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

    Neuronpedia

    INDEX
    Explanations

    exclamation points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (saved
    -0.08
    embros
    -0.07
     videoer
    -0.06
    assadors
    -0.06
     Royale
    -0.06
     heures
    -0.06
    ámara
    -0.06
     membres
    -0.06
    igham
    -0.06
     blanc
    -0.06
    POSITIVE LOGITS
     isinstance
    0.07
    SHOT
    0.06
     Strip
    0.06
     CNN
    0.06
    !↵↵↵↵↵↵
    0.06
    not
    0.06
     pian
    0.06
    _CHECK
    0.06
     (
↵
    0.06
     Unary
    0.06
    Act Density 0.004%

    No Known Activations