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

    Neuronpedia

    INDEX
    Explanations

    improving Open, writer revising, calculate this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Setelah
    0.44
    ями
    0.41
     ต่อ
    0.40
     당
    0.40
    աց
    0.40
     当
    0.39
     Когда
    0.39
     Etiam
    0.38
     Ketika
    0.38
     mana
    0.38
    POSITIVE LOGITS
     मुगल
    0.43
     Scotch
    0.41
    thinmathspace
    0.41
    Scot
    0.40
    शिला
    0.38
    lies
    0.38
     Crock
    0.37
    虫
    0.37
    indexing
    0.37
    ApiCalls
    0.36
    Act Density 0.000%

    No Known Activations