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

    Neuronpedia

    INDEX
    Explanations

    ya

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ambda
    -0.06
    公開
    -0.06
     ****
    -0.06
    edit
    -0.06
     sizeof
    -0.06
     paternal
    -0.06
     diplomatic
    -0.06
    (ro
    -0.06
     cuffs
    -0.06
     "..
    -0.05
    POSITIVE LOGITS
    ssa
    0.08
    uso
    0.07
     hayal
    0.07
    -preview
    0.06
     Monterey
    0.06
     عالية
    0.06
     brilliantly
    0.06
    HA
    0.06
     Mona
    0.06
    anya
    0.06
    Act Density 0.009%

    No Known Activations