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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maternal
    -0.07
     �
    -0.07
    ηγ
    -0.06
     stavu
    -0.06
     çocuğ
    -0.06
     hlavu
    -0.06
    ışık
    -0.06
    ầ
    -0.06
    _usage
    -0.06
     součas
    -0.06
    POSITIVE LOGITS
    )}"↵
    0.07
    参考
    0.07
     assessing
    0.06
    544
    0.06
     Form
    0.06
    model
    0.06
    771
    0.06
    dney
    0.06
     Generated
    0.06
    urable
    0.06
    Act Density 0.002%

    No Known Activations