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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [h
    -0.07
    仔
    -0.06
    fg
    -0.06
     jou
    -0.06
    izzo
    -0.06
     elephant
    -0.06
    edit
    -0.06
    (now
    -0.06
    ạ
    -0.06
     Hindu
    -0.06
    POSITIVE LOGITS
    ичний
    0.07
    	    ↵
    0.07
     ):↵
    0.07
    '])↵
    0.07
    ']↵
    0.06
    	        ↵
    0.06
    "))
↵
    0.06
     Chairs
    0.06
     dna
    0.06
     eventually
    0.06
    Act Density 0.037%

    No Known Activations