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

    Neuronpedia

    INDEX
    Explanations

    influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('=
    -0.06
     Carry
    -0.06
    \/
    -0.06
    하려
    -0.06
     гост
    -0.06
     المش
    -0.06
    _RESERVED
    -0.06
    _TX
    -0.06
    gw
    -0.06
    _dev
    -0.06
    POSITIVE LOGITS
    owied
    0.07
     residual
    0.06
    _ZONE
    0.06
    Acknowled
    0.06
     textured
    0.06
    FLT
    0.06
     mit
    0.06
    /grid
    0.06
    checkBox
    0.06
    ‌گذ
    0.06
    Act Density 0.044%

    No Known Activations