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

    Neuronpedia

    INDEX
    Explanations

    covering indexes and foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reset
    -0.08
     professional
    -0.08
     scaling
    -0.08
    .reset
    -0.07
    caling
    -0.07
     Salman
    -0.07
     scaled
    -0.07
     ergonom
    -0.07
    Sunday
    -0.07
    .today
    -0.07
    POSITIVE LOGITS
     toit
    0.08
     требуется
    0.08
     Regul
    0.08
     Друг
    0.08
     wanting
    0.08
     மற்ற
    0.08
     என்ப
    0.08
    IFI
    0.07
    	values
    0.07
    payments
    0.07
    Act Density 0.001%

    No Known Activations