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

    Neuronpedia

    INDEX
    Explanations

    energy and studio work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    삐
    0.39
     XNUMX
    0.39
    ppes
    0.38
     fifteen
    0.38
     hasten
    0.38
     translated
    0.37
    KIS
    0.37
    ப்படம்
    0.37
    {{\
    0.37
    MOT
    0.36
    POSITIVE LOGITS
     presidents
    0.45
     senators
    0.44
     bodhis
    0.40
     شرایط
    0.40
     eukary
    0.40
     पत्रकारों
    0.40
     அலுவலக
    0.40
    萼
    0.40
     Annu
    0.39
    ڑھ
    0.39
    Act Density 0.001%

    No Known Activations