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

    Neuronpedia

    INDEX
    Explanations

    liberal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dice
    -0.07
     Autumn
    -0.07
    例如
    -0.06
     тщ
    -0.06
     เง
    -0.06
    .staff
    -0.06
     ∈
    -0.06
    ød
    -0.06
    rangle
    -0.06
     congen
    -0.06
    POSITIVE LOGITS
     Liberal
    0.10
     liberal
    0.09
     liber
    0.08
    .club
    0.07
     liberals
    0.07
    ivor
    0.07
    ctic
    0.07
     Harbor
    0.07
     thinly
    0.07
     harbor
    0.07
    Act Density 0.009%

    No Known Activations