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

    Neuronpedia

    INDEX
    Explanations

    Technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAKE
    -0.07
     hayatı
    -0.07
    あるい
    -0.07
    _ON
    -0.07
     defeated
    -0.07
     gerade
    -0.07
    .pg
    -0.06
    .setHorizontalAlignment
    -0.06
    Ӕ
    -0.06
     메
    -0.06
    POSITIVE LOGITS
    <Order
    0.08
    ApiKey
    0.07
    arters
    0.07
    highlight
    0.07
     éxito
    0.07
     Mark
    0.07
    clipboard
    0.07
    cls
    0.07
    𝐭
    0.07
     extract
    0.07
    Act Density 0.138%

    No Known Activations