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

    Neuronpedia

    INDEX
    Explanations

    code/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	E
    -0.06
    那个
    -0.06
    PubMed
    -0.06
     preset
    -0.06
    ема
    -0.06
     personal
    -0.06
    -0.06
    -0.06
    电影
    -0.05
    аними
    -0.05
    POSITIVE LOGITS
    [top
    0.09
    (dm
    0.07
    .setSelection
    0.07
    (sequence
    0.07
    .transitions
    0.07
    (rules
    0.07
     галузі
    0.07
     Feinstein
    0.06
    ('.'
    0.06
    /about
    0.06
    Act Density 0.001%

    No Known Activations