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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     premi
    -0.07
     __("
    -0.06
     ModelRenderer
    -0.06
     जय
    -0.06
    	ID
    -0.06
     footh
    -0.06
    _DECREF
    -0.06
    к
    -0.06
    社
    -0.06
    ../
    -0.05
    POSITIVE LOGITS
     başarılı
    0.07
     notification
    0.07
    .parseColor
    0.07
    .Quit
    0.06
    lose
    0.06
     demande
    0.06
     normalization
    0.06
    _LOAD
    0.06
    iterr
    0.06
     Losing
    0.06
    Act Density 0.004%

    No Known Activations