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

    Neuronpedia

    INDEX
    Explanations

    approximate costs, prices, even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FRA
    0.40
    ায়ে
    0.38
    фри
    0.37
    ajaan
    0.37
    fra
    0.37
     बनाम
    0.37
     पुरस्कृत
    0.37
     recuperación
    0.37
     FRA
    0.36
     Fra
    0.36
    POSITIVE LOGITS
    Condensed
    0.46
    Kir
    0.41
    Crist
    0.39
    Phen
    0.39
    Giz
    0.39
    Corner
    0.39
    Phenyl
    0.39
    even
    0.38
    phenyl
    0.38
     даже
    0.38
    Act Density 0.000%

    No Known Activations