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

    Neuronpedia

    INDEX
    Explanations

    mass-energy equivalence, Lactobacillus, display

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ke
    0.66
     szabad
    0.65
     Sky
    0.64
     Ke
    0.62
    arna
    0.61
     कोट
    0.61
     kosten
    0.60
    Ke
    0.58
    blad
    0.58
    eszcze
    0.57
    POSITIVE LOGITS
    ர்த்தி
    0.82
     NCC
    0.81
    NP
    0.81
    NS
    0.79
     display
    0.77
     NHT
    0.77
    چال
    0.76
     displaying
    0.76
     NPM
    0.75
    LP
    0.74
    Act Density 0.002%

    No Known Activations