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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Final
    -0.07
    Final
    -0.07
     Ekim
    -0.06
     Fallout
    -0.06
     speaks
    -0.06
    確
    -0.06
     Nach
    -0.06
     dictates
    -0.06
     reveals
    -0.06
     stark
    -0.06
    POSITIVE LOGITS
    '/>↵
    0.07
    _hand
    0.07
    >";↵↵
    0.06
    }");↵↵
    0.06
    _app
    0.06
    .leave
    0.06
    чки
    0.06
     INTO
    0.06
    */)
    0.06
    hand
    0.06
    Act Density 0.002%

    No Known Activations