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

    Neuronpedia

    INDEX
    Explanations

    code and specifications related to web resource management and testing

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

    testing and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.56
    CPtr
    -0.49
    __':
    -0.47
     betweenstory
    -0.44
    writeFieldEnd
    -0.43
    ########.
    -0.42
    EndContext
    -0.42
    =$?
    -0.41
     dAtA
    -0.41
    featureID
    -0.40
    POSITIVE LOGITS
    muñeca
    0.44
    AntiForgeryToken
    0.44
     Sahib
    0.42
     officiers
    0.42
     HasFactory
    0.40
     contagios
    0.39
    blico
    0.39
    pantalón
    0.39
     ausser
    0.39
     unters
    0.38
    Act Density 0.037%

    No Known Activations