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

    Neuronpedia

    INDEX
    Explanations

    tabula rasa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hany
    0.41
    亗
    0.40
     NSMutable
    0.39
     tanti
    0.39
    ோம்
    0.39
    ContentType
    0.37
     g
    0.37
     kome
    0.37
     hemat
    0.36
     compounding
    0.36
    POSITIVE LOGITS
    birds
    0.45
    Animals
    0.41
    Birds
    0.41
    newspaper
    0.41
    angaroo
    0.39
    Dogs
    0.39
    Το
    0.39
    无人
    0.39
    ιτε
    0.38
    ierto
    0.38
    Act Density 0.000%

    No Known Activations