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

    Neuronpedia

    INDEX
    Explanations

    variable definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ROff
    0.48
     архіви
    0.43
    inalis
    0.42
    Recorder
    0.39
    fehlung
    0.39
    rukh
    0.38
     背景
    0.38
    RetResult
    0.37
     Algebras
    0.37
     Diaspora
    0.37
    POSITIVE LOGITS
     number
    0.51
     número
    0.51
     the
    0.48
     Número
    0.46
     comes
    0.44
     identifies
    0.42
    也就是
    0.42
     expresses
    0.42
     aka
    0.41
    分為
    0.41
    Act Density 0.003%

    No Known Activations