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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awks
    -0.06
     speech
    -0.06
    BERS
    -0.06
    tuk
    -0.06
    .sec
    -0.06
     comp
    -0.06
     JSON
    -0.06
     دلیل
    -0.06
    :key
    -0.05
    aign
    -0.05
    POSITIVE LOGITS
    efore
    0.07
    _GF
    0.07
     estoy
    0.07
    _building
    0.07
     panorama
    0.06
     Josef
    0.06
     EAST
    0.06
    лата
    0.06
     ($_
    0.06
     ",↵
    0.06
    Act Density 0.000%

    No Known Activations