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

    Neuronpedia

    INDEX
    Explanations

    subjective expressions and opinions

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

    likely or seems like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.48
    RTEX
    -0.41
    -0.41
    HttpConnection
    -0.40
    hots
    -0.39
    ModelSerializer
    -0.38
    ALM
    -0.37
     klok
    -0.36
     Outsourcing
    -0.36
     vuelta
    -0.36
    POSITIVE LOGITS
    UnsafeEnabled
    0.48
    EditorBrowsable
    0.46
     @"/
    0.46
    WriteBarrier
    0.46
    djangoproject
    0.44
     विश्वसनीयता
    0.44
     defaultstate
    0.40
     Title
    0.39
     confusion
    0.38
     disappointing
    0.37
    Act Density 0.048%

    No Known Activations