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

    Neuronpedia

    INDEX
    Explanations

    hab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مد
    -0.07
     fois
    -0.06
    ª
    -0.06
     рівні
    -0.06
    indrome
    -0.06
     vois
    -0.06
    launcher
    -0.06
    _endpoint
    -0.06
     Pierre
    -0.06
    theorem
    -0.06
    POSITIVE LOGITS
    .IN
    0.06
    SHARE
    0.06
     Пос
    0.06
    RELATED
    0.06
    STANCE
    0.06
    ULA
    0.06
    american
    0.06
    ór
    0.06
     prospect
    0.06
     truthful
    0.06
    Act Density 0.002%

    No Known Activations