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

    Neuronpedia

    INDEX
    Explanations

    welfare programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durum
    -0.07
    nn
    -0.07
     ensemble
    -0.06
    ocate
    -0.06
     inference
    -0.06
    -b
    -0.06
     все
    -0.06
    locs
    -0.06
    stered
    -0.06
    lesi
    -0.06
    POSITIVE LOGITS
     proud
    0.07
    /off
    0.07
     Rich
    0.06
    バイ
    0.06
    (center
    0.06
     清
    0.06
     onslaught
    0.06
     přiv
    0.06
    grown
    0.06
     DAC
    0.06
    Act Density 0.051%

    No Known Activations