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

    Neuronpedia

    INDEX
    Explanations

    conversation/interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lấy
    -0.07
    eps
    -0.06
     nuôi
    -0.06
    ูช
    -0.06
    верд
    -0.06
    -config
    -0.06
    yro
    -0.06
    simp
    -0.06
    ामल
    -0.06
    ajo
    -0.06
    POSITIVE LOGITS
     sincer
    0.08
     illumination
    0.07
    (er
    0.06
    _WORLD
    0.06
     Hook
    0.06
     endlessly
    0.06
     ян
    0.06
    ';↵
    0.06
     처리
    0.06
     ara
    0.06
    Act Density 0.003%

    No Known Activations