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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tranh
    -0.07
    Ver
    -0.07
    [\
    -0.06
    創
    -0.06
     использовать
    -0.06
    '>"
    -0.06
    	fprintf
    -0.06
     Dec
    -0.06
     striving
    -0.06
    Hong
    -0.06
    POSITIVE LOGITS
     pickup
    0.10
     pickups
    0.10
     Pickup
    0.08
     récup
    0.08
    лара
    0.07
     catches
    0.07
    ิโน
    0.07
    jiště
    0.07
     Recover
    0.07
     ін
    0.06
    Act Density 0.010%

    No Known Activations