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

    Neuronpedia

    INDEX
    Explanations

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fif
    -0.06
    caf
    -0.06
     shifting
    -0.06
    []=
    -0.06
    AREST
    -0.06
     "&
    -0.06
     às
    -0.06
     vestib
    -0.06
    Approx
    -0.06
    if
    -0.06
    POSITIVE LOGITS
     done
    0.12
     Done
    0.11
    Done
    0.09
    _done
    0.08
     DONE
    0.08
    DONE
    0.08
    someone
    0.08
     gone
    0.08
    .done
    0.08
    	done
    0.08
    Act Density 0.018%

    No Known Activations