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

    Neuronpedia

    INDEX
    Explanations

    visit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acist
    -0.07
     Laser
    -0.07
    자료
    -0.06
     aston
    -0.06
     dao
    -0.06
     scripts
    -0.06
     automated
    -0.06
     Fant
    -0.06
     setuptools
    -0.06
     northern
    -0.06
    POSITIVE LOGITS
     직
    0.07
     Brady
    0.07
     arbitrary
    0.06
    Throughout
    0.06
     Truy
    0.06
    -alpha
    0.06
    ằm
    0.06
    .setFont
    0.06
    ffi
    0.06
    -अ
    0.06
    Act Density 0.024%

    No Known Activations