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

    Neuronpedia

    INDEX
    Explanations

    what exists or comes before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    },
    0.53
    ED
    0.50
     as
    0.46
    hos
    0.45
    )}.
    0.45
    by
    0.44
    k
    0.44
    ions
    0.43
    )},
    0.43
    ks
    0.43
    POSITIVE LOGITS
    ړو
    0.60
    Tuple
    0.58
     humides
    0.54
     localidad
    0.52
     सर्
    0.50
     শরীরের
    0.50
    ζί
    0.49
     ટ્ર
    0.49
     ট্র
    0.49
    SwingConstants
    0.48
    Act Density 0.000%

    No Known Activations