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

    Neuronpedia

    INDEX
    Explanations

    coarse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ql
    -0.08
     цар
    -0.07
    /embed
    -0.07
     yıllık
    -0.07
    _tweets
    -0.07
     Закону
    -0.06
    _np
    -0.06
    (segment
    -0.06
     xyz
    -0.06
    tip
    -0.06
    POSITIVE LOGITS
     coarse
    0.16
    upil
    0.07
    粗
    0.07
     Coach
    0.07
    urf
    0.06
     Marble
    0.06
    FOUNDATION
    0.06
    賽
    0.06
     carrot
    0.06
     oath
    0.06
    Act Density 0.001%

    No Known Activations