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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owl
    -0.07
    .Application
    -0.07
    モン
    -0.07
    ische
    -0.06
    ekte
    -0.06
     LeBron
    -0.06
    }}>
    -0.06
    FINITE
    -0.06
    blend
    -0.06
    (non
    -0.06
    POSITIVE LOGITS
    井
    0.07
    Hay
    0.06
     raced
    0.06
     specialists
    0.06
    layarak
    0.06
     الله
    0.06
     nails
    0.06
     Rein
    0.06
    Coffee
    0.06
     clarification
    0.06
    Act Density 0.013%

    No Known Activations