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

    Neuronpedia

    INDEX
    Explanations

    technical discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _magic
    -0.07
    _TW
    -0.07
     Volt
    -0.07
     omitted
    -0.07
    .Rect
    -0.06
     {}↵
    -0.06
     Kennedy
    -0.06
     Tomas
    -0.06
     {}↵↵
    -0.06
     Вас
    -0.06
    POSITIVE LOGITS
     important
    0.06
     SUB
    0.06
     harass
    0.06
    (G
    0.06
    RegExp
    0.06
    -conscious
    0.06
    actal
    0.06
    こちら
    0.06
    .userInteractionEnabled
    0.06
    ENSITY
    0.06
    Act Density 0.275%

    No Known Activations