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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bek
    -0.07
     ther
    -0.06
     commits
    -0.06
    ňování
    -0.06
     pandemic
    -0.06
     cambios
    -0.06
    arken
    -0.06
    _distances
    -0.06
    signal
    -0.06
    증
    -0.06
    POSITIVE LOGITS
    ROWN
    0.07
     Buckley
    0.06
    SELF
    0.06
     Dickinson
    0.06
    129
    0.06
     Hammond
    0.06
     snack
    0.06
     profesyonel
    0.06
    emacs
    0.06
     встре
    0.06
    Act Density 0.015%

    No Known Activations