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

    Neuronpedia

    INDEX
    Explanations

    colors and chemicals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.96
    as
    0.88
    or
    0.77
    ное
    0.77
     digitization
    0.74
     necessity
    0.73
     repositories
    0.71
     कोस
    0.71
     junction
    0.71
     جون
    0.71
    POSITIVE LOGITS
    ยิน
    1.04
    ının
    0.97
     envolvendo
    0.93
     fala
    0.93
    CH
    0.88
    ज
    0.88
    goers
    0.86
    ी
    0.85
    てください
    0.83
     πολλ
    0.83
    Act Density 0.000%

    No Known Activations