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

    Neuronpedia

    INDEX
    Explanations

    anomaly detection, cool-down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ærer
    0.73
    plural
    0.70
     ভাষা
    0.69
     devlet
    0.68
    コスメ
    0.67
    ReadAll
    0.65
     맞는
    0.64
     indeks
    0.64
     Taste
    0.64
     índice
    0.63
    POSITIVE LOGITS
    eb
    0.73
    Hs
    0.69
    nesday
    0.68
    Mem
    0.65
     mem
    0.65
     Mem
    0.64
    മൂഹ
    0.62
     Regions
    0.61
    Node
    0.61
    सों
    0.61
    Act Density 0.009%

    No Known Activations