Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of conditions and requirements related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Japanese particles/grammar

    np_acts-logits-general · gemini-2.0-flash

    programming symbols and Japanese particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assium
    -0.35
     dictadura
    -0.34
    Hozzáférés
    -0.34
     mandatario
    -0.34
     potenciales
    -0.33
    -0.33
     таким
    -0.33
    zmm
    -0.32
     donné
    -0.32
    Loving
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.57
    Бахар
    0.55
    |=\
    0.54
    oneofs
    0.53
    pters
    0.52
    EndContext
    0.50
     CreateTagHelper
    0.50
    GEBURTSDATUM
    0.49
     Autorizaciones
    0.48
    UserScript
    0.48
    Act Density 0.042%

    No Known Activations