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

    Neuronpedia

    INDEX
    Explanations

    less than or equal to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mining
    -0.08
    wards
    -0.08
     awards
    -0.08
     repeats
    -0.07
     ув
    -0.07
     ontology
    -0.07
     deprivation
    -0.07
    (draw
    -0.07
     award
    -0.07
     summit
    -0.07
    POSITIVE LOGITS
     bounding
    0.10
     bounded
    0.10
    bounded
    0.10
     bounds
    0.10
    Bounding
    0.09
    Magnitude
    0.09
     Bounds
    0.09
     magnitude
    0.09
     Lips
    0.09
    bounding
    0.09
    Act Density 0.009%

    No Known Activations