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

    Neuronpedia

    INDEX
    Explanations

    party

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ersch
    0.79
    ed
    0.79
    fordern
    0.74
    видно
    0.73
    arcía
    0.72
    er
    0.72
    ಿಸಿಕೊಳ್ಳ
    0.71
    erb
    0.70
    feitura
    0.69
     così
    0.68
    POSITIVE LOGITS
     hac
    0.85
     ith
    0.78
     Qg
    0.78
     Thunder
    0.77
     sm
    0.76
    மிட
    0.75
     pistons
    0.74
     Proteins
    0.74
     bith
    0.74
     satellites
    0.74
    Act Density 0.000%

    No Known Activations