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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rosso
    -0.09
     fax
    -0.08
     grâce
    -0.08
     اللا
    -0.08
    scratch
    -0.07
     propriétaire
    -0.07
     realidad
    -0.07
     מצ
    -0.07
    箍
    -0.07
     Sheriff
    -0.07
    POSITIVE LOGITS
    :'',↵
    0.07
    ﮟ
    0.07
     Serif
    0.07
    愭
    0.07
    _verified
    0.06
     Edition
    0.06
     Flexible
    0.06
    -${
    0.06
     ''
↵
    0.06
    :')↵
    0.06
    Act Density 0.000%

    No Known Activations