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

    Neuronpedia

    INDEX
    Explanations

    amstel, amstrad, astc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usine
    0.51
    unprocessable
    0.50
    inale
    0.48
    팡
    0.43
    liny
    0.43
    ahin
    0.40
    Cant
    0.39
    seid
    0.39
     canes
    0.39
    ნიშვნ
    0.39
    POSITIVE LOGITS
     architectures
    0.42
    gpu
    0.41
     Hypothesis
    0.41
     Utilization
    0.40
     GPU
    0.39
    hla
    0.39
     Ко
    0.38
    诡
    0.38
     באופן
    0.37
     ethics
    0.37
    Act Density 0.000%

    No Known Activations