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

    Neuronpedia

    INDEX
    Explanations

    po

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chorus
    -0.07
     stir
    -0.07
     tub
    -0.07
    feof
    -0.06
     برد
    -0.06
    öz
    -0.06
     mayores
    -0.06
    ademic
    -0.06
    ्रत
    -0.06
    oldur
    -0.06
    POSITIVE LOGITS
     po
    0.33
     Po
    0.18
    Po
    0.14
    -po
    0.14
    po
    0.12
    _po
    0.11
    (po
    0.11
     PO
    0.09
    .po
    0.08
    _PO
    0.08
    Act Density 0.008%

    No Known Activations