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

    Neuronpedia

    INDEX
    Explanations

    conservative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PIN
    -0.06
    Ram
    -0.06
    圆
    -0.06
    _forms
    -0.06
    tı
    -0.06
     >=
    -0.06
    ×</
    -0.06
    YNC
    -0.06
    ätz
    -0.06
    becue
    -0.06
    POSITIVE LOGITS
     cork
    0.07
     Locke
    0.07
     sene
    0.06
     축
    0.06
     शत
    0.06
     Duis
    0.06
     Churchill
    0.06
    .Floor
    0.06
    Neutral
    0.06
    �
    0.06
    Act Density 0.015%

    No Known Activations