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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _KP
    -0.07
    běh
    -0.07
    -more
    -0.07
     atof
    -0.07
    िवर
    -0.06
    ‌است
    -0.06
     kiếm
    -0.06
    ddb
    -0.06
    /kubernetes
    -0.06
     кілька
    -0.06
    POSITIVE LOGITS
     каждого
    0.07
    reau
    0.06
     complic
    0.06
    /example
    0.06
     downstairs
    0.06
     gradually
    0.06
     apartments
    0.06
    Styles
    0.06
     سخ
    0.06
     Ho
    0.06
    Act Density 0.005%

    No Known Activations