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

    Neuronpedia

    INDEX
    Explanations

    Gener

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .byte
    -0.07
    ife
    -0.07
    .Me
    -0.06
     ई
    -0.06
     trùng
    -0.06
     gameId
    -0.06
    eking
    -0.06
     PIE
    -0.06
     پي
    -0.06
     बद
    -0.06
    POSITIVE LOGITS
    	active
    0.07
     Univ
    0.06
    ین
    0.06
     expensive
    0.06
     principalTable
    0.06
    $client
    0.06
     constructor
    0.06
     irgend
    0.06
     출연
    0.06
     swung
    0.06
    Act Density 0.003%

    No Known Activations