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

    Neuronpedia

    INDEX
    Explanations

    smallest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =:
    -0.07
    (latitude
    -0.07
     Icon
    -0.06
    __.__
    -0.06
    gorith
    -0.06
    841
    -0.06
    .pin
    -0.06
    ipt
    -0.06
     {//
    -0.06
    clf
    -0.06
    POSITIVE LOGITS
    50
    0.07
     lows
    0.07
     eerie
    0.06
     ут
    0.06
    stance
    0.06
    _rm
    0.06
    Spot
    0.06
    ित
    0.06
    جاج
    0.06
     cường
    0.06
    Act Density 0.002%

    No Known Activations