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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ěla
    -0.07
    هل
    -0.07
     clashed
    -0.07
     toda
    -0.07
     техничес
    -0.06
    機能
    -0.06
    pegawai
    -0.06
    اوری
    -0.06
     Felipe
    -0.06
     queries
    -0.06
    POSITIVE LOGITS
     setInput
    0.08
    .fname
    0.06
    _ground
    0.06
    (array
    0.06
    ,))↵
    0.06
    .tile
    0.06
    /mp
    0.06
     "}
    0.06
    -ce
    0.06
    िज
    0.06
    Act Density 0.005%

    No Known Activations