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

    Neuronpedia

    INDEX
    Explanations

    sans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INFO
    -0.07
    Eye
    -0.07
    /n
    -0.07
    وية
    -0.07
     zug
    -0.06
     Juice
    -0.06
    .Instance
    -0.06
    stru
    -0.06
    *&
    -0.06
     belirli
    -0.06
    POSITIVE LOGITS
     removeFromSuperview
    0.07
     char
    0.06
    렉
    0.06
     無
    0.06
     황
    0.06
    eren
    0.06
    �
    0.06
     buflen
    0.06
    맨
    0.06
     ++)↵
    0.06
    Act Density 0.001%

    No Known Activations