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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CONT
    -0.07
    USTER
    -0.07
     expressed
    -0.07
     다시
    -0.06
     travel
    -0.06
    _sg
    -0.06
     inhabitants
    -0.06
     flattened
    -0.06
    -not
    -0.06
    Into
    -0.06
    POSITIVE LOGITS
    าตรฐาน
    0.06
    FO
    0.06
    على
    0.06
    owel
    0.06
     cry
    0.06
     (("
    0.06
     können
    0.06
     poetic
    0.06
     vuel
    0.06
    van
    0.06
    Act Density 0.009%

    No Known Activations