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

    Neuronpedia

    INDEX
    Explanations

    acting character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Birthday
    -0.07
    (array
    -0.07
    goals
    -0.07
    engineering
    -0.06
    .bin
    -0.06
     scenarios
    -0.06
     zones
    -0.06
     pq
    -0.06
    figures
    -0.06
    یه
    -0.06
    POSITIVE LOGITS
     Mozilla
    0.07
    oooo
    0.06
    ozilla
    0.06
    adele
    0.06
     beide
    0.06
     права
    0.06
    =format
    0.06
    es
    0.06
    법
    0.06
     Rencontres
    0.06
    Act Density 0.010%

    No Known Activations