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

    Neuronpedia

    INDEX
    Explanations

    Released

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descargar
    -0.07
     Gratis
    -0.07
     sweet
    -0.07
    ضغ
    -0.07
     perg
    -0.07
    estination
    -0.06
     billed
    -0.06
    -specific
    -0.06
    采摘
    -0.06
    anium
    -0.06
    POSITIVE LOGITS
    毅
    0.07
    _DECLARE
    0.07
    lider
    0.06
    directive
    0.06
    鸷
    0.06
    三条
    0.06
    effective
    0.06
    Workbook
    0.06
    יכון
    0.06
    .units
    0.06
    Act Density 0.004%

    No Known Activations