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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    улю
    -0.07
    щают
    -0.06
     IDX
    -0.06
    	router
    -0.06
     лечение
    -0.06
    .feature
    -0.05
     FIR
    -0.05
    Returns
    -0.05
    .Global
    -0.05
     Tus
    -0.05
    POSITIVE LOGITS
    Mongo
    0.08
     remembering
    0.07
    &q
    0.07
    اسیون
    0.06
     graf
    0.06
     Behind
    0.06
    thood
    0.06
    iores
    0.06
     EntityState
    0.06
    -under
    0.06
    Act Density 0.011%

    No Known Activations