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

    Neuronpedia

    INDEX
    Explanations

    Style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _named
    -0.07
     Russ
    -0.06
    ptune
    -0.06
    Foo
    -0.06
    敦
    -0.06
     Fey
    -0.06
    чає
    -0.06
     înt
    -0.06
     AW
    -0.06
     shore
    -0.06
    POSITIVE LOGITS
    (selection
    0.07
    pedo
    0.06
    以外
    0.06
    -prev
    0.06
     incluso
    0.06
    ��索
    0.06
     [];
    0.06
    ipzig
    0.06
     Genre
    0.06
    Ghost
    0.06
    Act Density 0.009%

    No Known Activations