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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ậu
    -0.07
    pa
    -0.06
    ůž
    -0.06
     اون
    -0.06
    oles
    -0.06
     LOOP
    -0.06
     잠
    -0.06
    ायल
    -0.06
    iew
    -0.06
     permitting
    -0.06
    POSITIVE LOGITS
    ...</
    0.06
     ^{}
    0.06
    evin
    0.06
    SuppressLint
    0.06
    _filepath
    0.06
    Blake
    0.06
     geschichten
    0.06
    CTR
    0.06
     респ
    0.06
    letters
    0.06
    Act Density 2.541%

    No Known Activations