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

    Neuronpedia

    INDEX
    Explanations

    connecting items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plays
    0.55
     hanging
    0.53
     march
    0.52
    क्सीडेंट
    0.50
     पूरे
    0.44
    ഗ്രഹം
    0.43
    <unused10>
    0.42
     explored
    0.42
    İN
    0.42
    <unused4>
    0.42
    POSITIVE LOGITS
     आणि
    2.16
     и
    2.09
     và
    2.08
     and
    2.06
     અને
    2.06
    และ
    2.03
     और
    2.02
     மற்றும்
    1.99
     και
    1.96
     ਅਤੇ
    1.94
    Act Density 5.965%

    No Known Activations