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

    Neuronpedia

    INDEX
    Explanations

    Ram

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    laws
    0.44
    ្
    0.43
    ઢી
    0.40
    Els
    0.40
    ্বাস
    0.39
    corpor
    0.38
    Corpor
    0.38
    лося
    0.37
     Corporations
    0.36
    apiro
    0.36
    POSITIVE LOGITS
    ye
    0.40
    dden
    0.38
    अर्ज
    0.37
    ro
    0.37
    DAN
    0.36
     mái
    0.36
    će
    0.35
    ŕ
    0.35
     nak
    0.35
    Ro
    0.35
    Act Density 0.000%

    No Known Activations