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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?>"
    -0.07
     oscill
    -0.07
    煤
    -0.06
    707
    -0.06
     lighting
    -0.06
     Appe
    -0.06
    ¿
    -0.06
    99
    -0.06
    系統
    -0.06
    وى
    -0.06
    POSITIVE LOGITS
     ambitions
    0.07
     المخت
    0.06
    predicate
    0.06
    jamin
    0.06
     teş
    0.06
     Nüfus
    0.06
    orrect
    0.06
     ineligible
    0.06
    riday
    0.06
     अव
    0.06
    Act Density 0.014%

    No Known Activations