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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to ownership or personal connection

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

    our Privacy Policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſte
    -0.71
     ſch
    -0.69
    ftagPool
    -0.65
    saraba
    -0.63
     CreateTagHelper
    -0.62
     Monfieur
    -0.60
     AssemblyProduct
    -0.60
    ":[{
    -0.59
     ModelExpression
    -0.56
    ]")]
    -0.55
    POSITIVE LOGITS
     daños
    0.39
     palvel
    0.39
     emociones
    0.35
     interesa
    0.34
     žal
    0.34
     calentamiento
    0.34
     florales
    0.33
     perdiendo
    0.33
     intenciones
    0.33
     arbres
    0.33
    Act Density 0.000%

    No Known Activations