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

    Neuronpedia

    INDEX
    Explanations

    Prepositions/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asz
    -0.07
    many
    -0.07
    تش
    -0.06
    VIN
    -0.06
    utom
    -0.06
    105
    -0.06
    outs
    -0.06
    avan
    -0.06
    weekday
    -0.06
    _district
    -0.06
    POSITIVE LOGITS
     mar
    0.07
    ではない
    0.07
     міської
    0.07
     kys
    0.06
     Studies
    0.06
     мо
    0.06
     ख
    0.06
     Soda
    0.06
     CNS
    0.06
     subscript
    0.06
    Act Density 0.082%

    No Known Activations