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

    Neuronpedia

    INDEX
    Explanations

    statements of fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Human
    -0.08
    ाल
    -0.07
    Rx
    -0.07
     Spirit
    -0.07
     customers
    -0.06
     unpleasant
    -0.06
     ears
    -0.06
    Land
    -0.06
     shareholder
    -0.06
     future
    -0.06
    POSITIVE LOGITS
     redux
    0.07
     igual
    0.07
    ＿_
    0.07
     decorators
    0.06
     algae
    0.06
    _launcher
    0.06
    　j
    0.06
     posicion
    0.06
    üsü
    0.06
    �州
    0.06
    Act Density 0.254%

    No Known Activations