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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    velocity
    -0.07
    -quarters
    -0.07
    usto
    -0.06
    OfSize
    -0.06
    -defined
    -0.06
    acam
    -0.06
     rezerv
    -0.06
    โซ
    -0.06
    /bind
    -0.06
    Conditional
    -0.06
    POSITIVE LOGITS
    charger
    0.07
    	flash
    0.06
    inth
    0.06
     Hedge
    0.06
     refrigerator
    0.06
    popup
    0.06
     評価
    0.06
     BLOCK
    0.06
    "][
    0.06
    」，
    0.06
    Act Density 0.064%

    No Known Activations