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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ofilm
    -0.07
    Santa
    -0.06
    (previous
    -0.06
    (properties
    -0.06
    елов
    -0.06
     �
    -0.06
     redirect
    -0.06
    enuous
    -0.06
     keyst
    -0.06
     childish
    -0.06
    POSITIVE LOGITS
    作者
    0.07
     ammon
    0.07
     doub
    0.07
    idia
    0.07
     gi
    0.06
     Purdue
    0.06
    มหาว
    0.06
    							↵
    0.06
     neut
    0.06
    ♥
    0.06
    Act Density 0.023%

    No Known Activations