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

    Neuronpedia

    INDEX
    Explanations

    Historical events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Keywords
    -0.07
    cipher
    -0.06
     respir
    -0.06
    .right
    -0.06
    top
    -0.06
    ve
    -0.06
    uggage
    -0.06
    ervention
    -0.06
    กฎหมาย
    -0.06
    res
    -0.06
    POSITIVE LOGITS
     vá
    0.07
    >}'
    0.07
     kural
    0.06
    ',$
    0.06
    �
    0.06
    !!,
    0.06
     небольш
    0.06
    يرة
    0.06
    เศษ
    0.06
    )[-
    0.06
    Act Density 0.083%

    No Known Activations