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

    Neuronpedia

    INDEX
    Explanations

    names and proper nouns, particularly surnames or titles

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

    Followed by a lowercase letter

    np_acts-logits-general · gemini-2.0-flash

    McDougald names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -1.04
     Мексичка
    -0.95
    LEncoder
    -0.84
    uxxxx
    -0.83
    IntoConstraints
    -0.83
    contentLoaded
    -0.82
    Personendaten
    -0.82
    InitVars
    -0.79
    脚注の使い方
    -0.79
    SpringRunner
    -0.77
    POSITIVE LOGITS
    ough
    0.49
    arty
    0.46
    Str
    0.45
      
    0.45
     ex
    0.45
     spending
    0.44
     Str
    0.44
     VIDEOTAPE
    0.43
    ahan
    0.43
    a
    0.42
    Act Density 0.177%

    No Known Activations