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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    请选择
    -0.06
    atsby
    -0.06
    (primary
    -0.06
    (ray
    -0.06
    ottesville
    -0.06
    (reference
    -0.06
     reconcile
    -0.06
    ’)
    -0.06
     Melee
    -0.06
    _sensor
    -0.06
    POSITIVE LOGITS
     Report
    0.08
     report
    0.08
    -update
    0.07
    	let
    0.07
     varchar
    0.06
     reports
    0.06
     Bob
    0.06
     adorned
    0.06
     breasts
    0.06
     Roulette
    0.06
    Act Density 0.012%

    No Known Activations