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

    Neuronpedia

    INDEX
    Explanations

    Hugging Face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    1.14
    Questa
    0.80
    До
    0.79
    전
    0.78
    New
    0.77
    ف
    0.77
    it
    0.77
    ad
    0.77
    ap
    0.76
    Die
    0.75
    POSITIVE LOGITS
    :
    0.96
    ер
    0.86
    еха
    0.73
    ៥
    0.72
    ៤
    0.70
     financiera
    0.68
    ّر
    0.65
     personnelle
    0.64
     MAINTENANCE
    0.64
    ៦
    0.63
    Act Density 0.042%

    No Known Activations