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

    Neuronpedia

    INDEX
    Explanations

    Code/abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .S
    -0.07
    -s
    -0.07
    .assertThat
    -0.07
    amples
    -0.07
    -S
    -0.07
     Share
    -0.06
    199
    -0.06
    .Spec
    -0.06
     shredded
    -0.06
    .Socket
    -0.06
    POSITIVE LOGITS
    _low
    0.07
    -------↵↵
    0.07
    lette
    0.06
    822
    0.06
    까지
    0.06
    mé
    0.06
    宝
    0.06
    _money
    0.06
     Notre
    0.06
    Virginia
    0.06
    Act Density 3.605%

    No Known Activations