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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ctrl
    -0.07
     campos
    -0.07
    its
    -0.07
    obuf
    -0.06
    ependency
    -0.06
    -Semit
    -0.06
    idan
    -0.06
    ATIONS
    -0.06
    simulate
    -0.06
     exemplary
    -0.06
    POSITIVE LOGITS
     ];↵
    0.07
     вниз
    0.07
     важ
    0.06
    _check
    0.06
     tabPage
    0.06
    There
    0.06
    هاي
    0.06
     Phelps
    0.06
    浅
    0.06
     aplik
    0.06
    Act Density 0.000%

    No Known Activations