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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attractiveness
    -0.08
    optimizer
    -0.07
    IClient
    -0.07
    Damage
    -0.07
    เสน
    -0.06
    OfDay
    -0.06
     trồng
    -0.06
    	nodes
    -0.06
    _approx
    -0.06
    -best
    -0.06
    POSITIVE LOGITS
    Sex
    0.06
    _STORE
    0.06
     proving
    0.06
     Perc
    0.06
     Moved
    0.06
    ingular
    0.06
     Garmin
    0.06
     Spell
    0.06
     waist
    0.06
     exponent
    0.06
    Act Density 0.002%

    No Known Activations