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
     Truman
    -0.07
    uslim
    -0.06
    ipl
    -0.06
     jams
    -0.06
    enario
    -0.06
     meme
    -0.06
    ersion
    -0.06
    düm
    -0.06
    -adjust
    -0.06
     Bout
    -0.06
    POSITIVE LOGITS
     Rotterdam
    0.07
    .Itoa
    0.07
    �
    0.07
     OTHERWISE
    0.06
     İng
    0.06
     FUNC
    0.06
     پژوهش
    0.06
    ")]↵↵
    0.06
     konu
    0.06
     decorating
    0.06
    Act Density 0.005%

    No Known Activations