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

    Neuronpedia

    INDEX
    Explanations

    released

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">//
    -0.58
     by
    -0.56
    they
    -0.54
    we
    -0.53
     exemplu
    -0.52
     jambes
    -0.51
     basah
    -0.51
     and
    -0.49
     manières
    -0.47
     beker
    -0.46
    POSITIVE LOGITS
     a
    1.38
     an
    1.05
     the
    0.88
    ]='\
    0.71
     EconPapers
    0.70
     its
    0.70
    expandindo
    0.69
    %")
    0.69
    LookAnd
    0.68
     Савезне
    0.68
    Act Density 0.006%

    No Known Activations