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

    Neuronpedia

    INDEX
    Explanations

    Once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ạp
    -0.07
    berg
    -0.07
    _-_
    -0.07
     atd
    -0.06
     cellFor
    -0.06
    갈
    -0.06
     İngiliz
    -0.06
    버
    -0.06
     жал
    -0.06
    StringUtil
    -0.06
    POSITIVE LOGITS
     Once
    0.12
    Once
    0.11
    once
    0.09
     once
    0.09
    .Once
    0.09
    lice
    0.08
    (ac
    0.07
    ce
    0.07
    /classes
    0.07
     ice
    0.07
    Act Density 0.014%

    No Known Activations