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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sy
    -0.07
    iare
    -0.07
     SEX
    -0.06
    �藏
    -0.06
    owered
    -0.06
     pane
    -0.06
    ωμα
    -0.06
    ibre
    -0.06
    vědom
    -0.06
     phil
    -0.06
    POSITIVE LOGITS
     olacak
    0.08
     СССР
    0.07
     fotbal
    0.06
    .XRLabel
    0.06
    .caption
    0.06
     İslâm
    0.06
     zástup
    0.06
     بق
    0.06
    conti
    0.06
    assets
    0.06
    Act Density 0.012%

    No Known Activations