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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     باست
    -0.07
    _truth
    -0.07
    announcement
    -0.06
    /she
    -0.06
     mining
    -0.06
    iado
    -0.06
    (matrix
    -0.05
    ivering
    -0.05
     radius
    -0.05
    eşit
    -0.05
    POSITIVE LOGITS
     langue
    0.07
     jas
    0.07
    gaben
    0.07
     YYS
    0.07
     TP
    0.07
     Además
    0.07
    olo
    0.07
     механіз
    0.06
    /welcome
    0.06
     fontFamily
    0.06
    Act Density 0.022%

    No Known Activations