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

    Neuronpedia

    INDEX
    Explanations

    Jupyter Notebook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يل
    1.16
    ان
    1.06
    ist
    0.99
    atura
    0.95
    zelfde
    0.93
    iked
    0.91
    ä
    0.91
    icl
    0.88
    тность
    0.85
    گاه
    0.85
    POSITIVE LOGITS
    fö
    0.95
     scur
    0.94
     exerc
    0.93
     persoane
    0.90
     Quar
    0.89
     piccoli
    0.89
    碜
    0.88
     chast
    0.88
     तुमच्या
    0.87
    ְ
    0.87
    Act Density 0.003%

    No Known Activations