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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loyd
    -0.07
    Defaults
    -0.06
    -being
    -0.06
    _'
    -0.06
     Clarke
    -0.06
    zero
    -0.06
    ClientId
    -0.06
    "
↵
↵
    -0.06
     人
    -0.06
    ／/
    -0.06
    POSITIVE LOGITS
    (prediction
    0.07
    )['
    0.07
    cin
    0.06
    .public
    0.06
    ONGLONG
    0.06
    _ci
    0.06
     دریافت
    0.06
    	cin
    0.06
    ính
    0.06
    ()?.
    0.06
    Act Density 0.001%

    No Known Activations