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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WPARAM
    -0.07
    ्�
    -0.07
    rut
    -0.07
    眉
    -0.06
     knull
    -0.06
     tố
    -0.06
     *,↵
    -0.06
    čné
    -0.06
    劇
    -0.06
    .csrf
    -0.06
    POSITIVE LOGITS
    ,...
    0.07
     CH
    0.06
    努力
    0.06
     اصفهان
    0.06
     persuade
    0.06
     coordinates
    0.06
    ระบ
    0.06
     Aboriginal
    0.06
    entious
    0.06
    ΙΝ
    0.06
    Act Density 0.049%

    No Known Activations