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

    Neuronpedia

    INDEX
    Explanations

    If

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     откры
    -0.06
     Sne
    -0.06
     تحلیل
    -0.06
     bullshit
    -0.06
     RESPONS
    -0.06
    CardBody
    -0.06
     Γκ
    -0.06
     Lazar
    -0.06
     เท
    -0.06
     bios
    -0.06
    POSITIVE LOGITS
    .black
    0.07
     movements
    0.07
     обы
    0.07
    aban
    0.07
     existing
    0.06
    rell
    0.06
     lien
    0.06
    inv
    0.06
    abit
    0.06
    filt
    0.06
    Act Density 0.002%

    No Known Activations