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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superst
    -0.07
    ك
    -0.06
     vari
    -0.06
     preds
    -0.06
    DIRECTORY
    -0.06
    _lost
    -0.06
    قع
    -0.06
    automation
    -0.06
     altura
    -0.06
    -Za
    -0.06
    POSITIVE LOGITS
     образования
    0.06
    尿
    0.06
    所有
    0.05
    ingerprint
    0.05
    .Kind
    0.05
     created
    0.05
    维
    0.05
     внутри
    0.05
    .clicked
    0.05
     подход
    0.05
    Act Density 0.000%

    No Known Activations