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

    Neuronpedia

    INDEX
    Explanations

    Actions versus words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _YELLOW
    -0.07
    Thirty
    -0.06
    .Mouse
    -0.06
     scor
    -0.06
    .cent
    -0.06
    帶
    -0.06
    uitable
    -0.06
     Parse
    -0.06
    偶
    -0.06
    ково
    -0.06
    POSITIVE LOGITS
    818
    0.07
    -ion
    0.06
     lieutenant
    0.06
    ANO
    0.06
    PositiveButton
    0.06
    romo
    0.06
     prostitute
    0.06
    raised
    0.06
    اوه
    0.06
    Drink
    0.06
    Act Density 0.176%

    No Known Activations