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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itting
    -0.07
    www
    -0.06
    norm
    -0.06
    fp
    -0.06
    τε
    -0.06
    _actions
    -0.06
    early
    -0.06
    َج
    -0.06
     SIGNAL
    -0.06
     cos
    -0.06
    POSITIVE LOGITS
     přen
    0.08
    Filed
    0.06
    _registers
    0.06
     agreg
    0.06
    霍
    0.06
    MASTER
    0.06
    .ReadByte
    0.06
    457
    0.06
     плен
    0.06
     yapacak
    0.06
    Act Density 0.002%

    No Known Activations