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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULO
    -0.07
    _frequency
    -0.06
     populist
    -0.06
    └
    -0.06
     compilers
    -0.06
    .toJSONString
    -0.06
    ighbor
    -0.06
    Warm
    -0.06
    сок
    -0.06
    Bro
    -0.06
    POSITIVE LOGITS
    ضم
    0.07
    �
    0.07
    收入
    0.07
    ดำ
    0.07
    .btnCancel
    0.06
     detain
    0.06
    leck
    0.06
    .Sm
    0.06
     troublesome
    0.06
    otten
    0.06
    Act Density 0.088%

    No Known Activations