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

    Neuronpedia

    INDEX
    Explanations

    random snippets of text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     in
    -0.07
     advocates
    -0.07
    政党
    -0.07
    ometrics
    -0.07
     transcend
    -0.06
     Uns
    -0.06
     verb
    -0.06
    一部分
    -0.06
    恨
    -0.06
     ears
    -0.06
    POSITIVE LOGITS
    셨
    0.07
    ◗
    0.07
    燏
    0.06
    🇭
    0.06
     relentlessly
    0.06
    笔记
    0.06
    겼
    0.06
    .PERMISSION
    0.06
    との
    0.06
    ẖ
    0.06
    Act Density 0.119%

    No Known Activations