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

    Neuronpedia

    INDEX
    Explanations

    lacking the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     невероят
    1.10
     juste
    1.09
     слегка
    1.00
     две
    0.98
     sadece
    0.95
     אך
    0.93
     három
    0.92
     شويه
    0.92
     különböző
    0.92
     trois
    0.91
    POSITIVE LOGITS
     any
    2.87
    任何
    2.61
     anything
    2.53
    any
    2.33
    Any
    2.23
    anything
    2.18
     Any
    2.17
     ANY
    2.10
     Anything
    2.09
     anywhere
    2.00
    Act Density 1.355%

    No Known Activations