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

    Neuronpedia

    INDEX
    Explanations

    error invalid unsupported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LetterIndex
    0.42
     leaner
    0.40
    Molecular
    0.39
     proiect
    0.39
    قیق
    0.38
     ją
    0.38
     ellipsoid
    0.38
     nuclei
    0.38
     niewiel
    0.37
     protop
    0.37
    POSITIVE LOGITS
    Invalid
    0.65
     Invalid
    0.61
    invalid
    0.55
     invalid
    0.53
     botched
    0.50
     inconsistency
    0.49
     inconsistent
    0.48
    不支持
    0.46
     Без
    0.46
    失效
    0.46
    Act Density 0.002%

    No Known Activations