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
    -0.06
     Buzz
    -0.06
     आर
    -0.06
    .created
    -0.06
    同意
    -0.06
     professionalism
    -0.06
    olith
    -0.06
     patience
    -0.05
     praise
    -0.05
    ()",
    -0.05
    POSITIVE LOGITS
     skvěl
    0.07
    'order
    0.07
     ’
    0.07
     peaks
    0.06
    _weight
    0.06
     наче
    0.06
     void
    0.06
    ảng
    0.06
    <bool
    0.06
    OPTIONS
    0.06
    Act Density 0.033%

    No Known Activations