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

    Neuronpedia

    INDEX
    Explanations

    instances of closing brackets and braces in code

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

    code closing braces and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.64
     كومونز
    -0.63
     AssemblyVersion
    -0.61
    帖最后由
    -0.61
     CreateTagHelper
    -0.58
     referenties
    -0.54
    styleType
    -0.53
     Réponses
    -0.53
     Winaray
    -0.53
    +#+
    -0.52
    POSITIVE LOGITS
     nocturno
    0.40
     móvil
    0.37
    esercito
    0.37
     fijo
    0.36
     panoramique
    0.36
    empêcher
    0.34
     muerto
    0.34
    enumii
    0.34
     scolaire
    0.33
     móviles
    0.32
    Act Density 0.007%

    No Known Activations