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

    Neuronpedia

    INDEX
    Explanations

    Some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =args
    -0.06
     thrift
    -0.06
     danh
    -0.06
     Radio
    -0.06
    �
    -0.06
    Stats
    -0.06
    emin
    -0.06
    央
    -0.06
     nood
    -0.06
    .snp
    -0.05
    POSITIVE LOGITS
    zept
    0.07
     харч
    0.07
     freezing
    0.07
    /payment
    0.06
     touching
    0.06
     PAY
    0.06
    _TEXTURE
    0.06
    (util
    0.06
    .Be
    0.06
    _Header
    0.06
    Act Density 0.000%

    No Known Activations