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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     המשת
    -0.08
    silent
    -0.07
    �
    -0.07
    薇
    -0.07
     afin
    -0.07
    خذ
    -0.07
    並同意
    -0.07
    .Mod
    -0.07
    并且
    -0.07
     Karen
    -0.07
    POSITIVE LOGITS
    nowrap
    0.08
     prominently
    0.08
     pp
    0.07
     prostituer
    0.07
    ʂ
    0.07
     engines
    0.07
     thinkers
    0.07
    cities
    0.07
     BFS
    0.06
    ろう
    0.06
    Act Density 0.001%

    No Known Activations