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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uz
    -0.07
    _book
    -0.07
    Raise
    -0.06
    snd
    -0.06
     later
    -0.06
    λλ
    -0.06
    Fs
    -0.06
     bord
    -0.06
    シュ
    -0.06
     tul
    -0.06
    POSITIVE LOGITS
    (pub
    0.07
    !");↵
    0.07
     Income
    0.07
    igmoid
    0.06
     WG
    0.06
     trụ
    0.06
     PTS
    0.06
     Pry
    0.06
    �
    0.06
     equipment
    0.06
    Act Density 0.029%

    No Known Activations