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

    Neuronpedia

    INDEX
    Explanations

    mathematical ranges and gaps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     respectable
    -0.08
     لتح
    -0.08
     honor
    -0.07
    ọc
    -0.07
    	try
    -0.07
    PK
    -0.07
     zetten
    -0.07
    .Member
    -0.07
     ويمكن
    -0.07
    etik
    -0.07
    POSITIVE LOGITS
     fehlen
    0.10
     между
    0.09
     tussen
    0.09
     unreachable
    0.09
     ontbreken
    0.09
     hagati
    0.09
     antara
    0.09
     pagitan
    0.09
     mellan
    0.09
     ontbre
    0.09
    Act Density 0.025%

    No Known Activations