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

    Neuronpedia

    INDEX
    Explanations

    can then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GLIGENCE
    -0.07
     ludicrous
    -0.06
    _dep
    -0.06
    htt
    -0.06
     courthouse
    -0.06
    027
    -0.06
    [Index
    -0.06
     yaygın
    -0.06
     техні
    -0.06
     zoom
    -0.06
    POSITIVE LOGITS
    imm
    0.07
     qualities
    0.06
    牌
    0.06
     diagnose
    0.06
    .hs
    0.06
    に
    0.06
    .object
    0.06
    　
    0.06
     oppon
    0.06
     ง
    0.06
    Act Density 0.055%

    No Known Activations