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

    Neuronpedia

    INDEX
    Explanations

    explaining code file naming conventions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inz
    0.69
     ums
    0.68
     intellect
    0.67
     ego
    0.63
     infusions
    0.62
     dull
    0.60
     indoctr
    0.59
    Insp
    0.58
     ave
    0.58
     midweek
    0.58
    POSITIVE LOGITS
    Milliseconds
    0.81
    čního
    0.77
    ˜</
    0.76
    ründ
    0.76
    ísticos
    0.74
    anilide
    0.72
    íncipe
    0.72
    findung
    0.71
     コード
    0.70
    éter
    0.70
    Act Density 0.001%

    No Known Activations