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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revolutions
    -0.06
     Republican
    -0.06
    sstream
    -0.06
     làm
    -0.06
    ด
    -0.06
     nuest
    -0.05
     обмеж
    -0.05
     Quickly
    -0.05
     //{
↵
    -0.05
     Reflex
    -0.05
    POSITIVE LOGITS
     copyright
    0.08
     apache
    0.08
     //=
    0.07
    へ
    0.07
    ักส
    0.07
    ■
    0.06
    idge
    0.06
     _,
    0.06
     prepared
    0.06
    —we
    0.06
    Act Density 0.025%

    No Known Activations