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

    Neuronpedia

    INDEX
    Explanations

    Stellantis, Helldivers, Stellate Ganglion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    1.47
    I
    1.27
    ين
    1.02
    ský
    1.00
     powied
    0.98
     {
    0.98
    td
    0.97
     (
    0.93
    erah
    0.92
    ع
    0.91
    POSITIVE LOGITS
    י
    1.51
    マ
    1.33
    سی
    1.32
    ле
    1.17
    ון
    1.17
    ט
    1.16
    用の
    1.15
    ב
    1.15
    ‌ای
    1.14
    ス
    1.13
    Act Density 0.000%

    No Known Activations