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

    Neuronpedia

    INDEX
    Explanations

    `__main__` block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gut
    0.56
    勻
    0.55
     वज
    0.54
     appell
    0.52
    Gut
    0.52
    gut
    0.51
     cr
    0.51
    Dimensional
    0.51
     contral
    0.51
     Trojans
    0.50
    POSITIVE LOGITS
     "__
    1.45
     '__
    1.41
     __
    1.13
    ("__
    0.92
    __
    0.90
    =="
    0.90
    ="__
    0.89
    (__
    0.86
     ___
    0.84
     (__
    0.84
    Act Density 0.027%

    No Known Activations