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

    Neuronpedia

    INDEX
    Explanations

    clock speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архівів
    0.44
     крат
    0.38
     бя
    0.38
    forderungen
    0.38
    unitas
    0.37
    inhard
    0.37
     определенных
    0.37
    ССР
    0.36
    ギュラー
    0.36
    лия
    0.36
    POSITIVE LOGITS
    仔
    0.41
     aise
    0.39
     swapped
    0.39
     hypnotic
    0.39
     sot
    0.39
     multicolored
    0.39
     lad
    0.38
     dicho
    0.38
     kerana
    0.38
     lovely
    0.38
    Act Density 0.000%

    No Known Activations