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

    Neuronpedia

    INDEX
    Explanations

    Now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chance
    -0.07
    abee
    -0.06
    Booking
    -0.06
     stepping
    -0.06
    elpers
    -0.06
     đang
    -0.06
    Autor
    -0.06
     Opr
    -0.06
     cabinet
    -0.06
    ication
    -0.06
    POSITIVE LOGITS
    getClass
    0.06
    365
    0.06
    том
    0.06
    .Encoding
    0.06
    rott
    0.06
    ตร
    0.06
    .steps
    0.06
    _Text
    0.06
    ileş
    0.06
     monks
    0.06
    Act Density 0.000%

    No Known Activations