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

    Neuronpedia

    INDEX
    Explanations

    research or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    των
    -0.07
     pseudo
    -0.07
     tsunami
    -0.07
    ोग
    -0.07
     провед
    -0.06
    (Border
    -0.06
     outskirts
    -0.06
     دهه
    -0.06
    .enums
    -0.06
    都会
    -0.06
    POSITIVE LOGITS
    โรงแรม
    0.07
     Nos
    0.06
    ISM
    0.06
     wars
    0.06
     TRY
    0.06
     PVOID
    0.06
     Whe
    0.06
    	fi
    0.06
                ↵↵
    0.06
     αρ
    0.06
    Act Density 0.000%

    No Known Activations