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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .docs
    -0.07
    بوب
    -0.07
    -cn
    -0.07
     Floral
    -0.07
    Issuer
    -0.07
    助
    -0.06
    _Menu
    -0.06
     affidavit
    -0.06
     urgent
    -0.06
     foresee
    -0.06
    POSITIVE LOGITS
    .workspace
    0.06
    リカ
    0.06
    ибли
    0.06
     гид
    0.06
     subparagraph
    0.06
    خص
    0.06
     сох
    0.05
     IsPlainOldData
    0.05
    .pushButton
    0.05
     каль
    0.05
    Act Density 0.029%

    No Known Activations