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

    Neuronpedia

    INDEX
    Explanations

    cul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oteca
    -0.07
    梅西
    -0.07
    .call
    -0.07
    ADE
    -0.07
    _IM
    -0.07
    bbing
    -0.06
    纯粹
    -0.06
    涅
    -0.06
     onc
    -0.06
    OCK
    -0.06
    POSITIVE LOGITS
     STATUS
    0.07
     Enabled
    0.07
     Structural
    0.07
    حار
    0.07
     заг
    0.07
    بو
    0.06
    htable
    0.06
    buf
    0.06
    た
    0.06
     Spiral
    0.06
    Act Density 0.001%

    No Known Activations