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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,copy
    -0.06
     fsm
    -0.06
     Sultan
    -0.06
     forensic
    -0.06
    .Component
    -0.06
    	bt
    -0.06
     Mourinho
    -0.06
    小伙
    -0.06
    .Some
    -0.06
     Jamal
    -0.06
    POSITIVE LOGITS
    DC
    0.08
    лев
    0.07
     HER
    0.07
    ize
    0.07
    REQUIRED
    0.06
    愉悦
    0.06
     outros
    0.06
    idos
    0.06
    ato
    0.06
     Ride
    0.06
    Act Density 0.062%

    No Known Activations