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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idges
    -0.07
    Meg
    -0.07
    =T
    -0.07
     CC
    -0.07
     zwyk
    -0.07
    阄
    -0.07
     OFFSET
    -0.07
    Table
    -0.07
    뻥
    -0.07
     Hold
    -0.07
    POSITIVE LOGITS
    ..
    0.08
    ايا
    0.07
    anj
    0.07
    ے
    0.07
     occupational
    0.06
     caracteres
    0.06
    טל
    0.06
    .cross
    0.06
     accompanied
    0.06
    Prem
    0.06
    Act Density 0.015%

    No Known Activations