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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Back
    -0.07
    .Back
    -0.07
     검색
    -0.06
     gunshot
    -0.06
    tains
    -0.06
    innitus
    -0.06
     beliefs
    -0.06
    ingers
    -0.06
    estado
    -0.05
     diesem
    -0.05
    POSITIVE LOGITS
     asymmetric
    0.07
    υτό
    0.06
    DidChange
    0.06
    漫
    0.06
     indemn
    0.06
    ालय
    0.06
    STRUCTOR
    0.06
    _VAR
    0.06
    mysqli
    0.06
    鼠
    0.06
    Act Density 0.005%

    No Known Activations