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

    Neuronpedia

    INDEX
    Explanations

    descriptive writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cosas
    -0.07
    _terminal
    -0.06
     欧美
    -0.06
     means
    -0.06
     díky
    -0.06
     Мет
    -0.06
     LOVE
    -0.06
     Hä
    -0.06
     ein
    -0.06
     pounded
    -0.05
    POSITIVE LOGITS
    onitor
    0.07
    /nav
    0.07
     usar
    0.06
    ปร
    0.06
    计算
    0.06
    ,b
    0.06
    intendent
    0.06
    akistan
    0.06
     vá
    0.06
     nást
    0.06
    Act Density 0.039%

    No Known Activations