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

    Neuronpedia

    INDEX
    Explanations

    Noisy/Informal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    966
    -0.06
    .COLUMN
    -0.06
     iletişim
    -0.06
    folio
    -0.06
     ArgumentOutOfRangeException
    -0.06
     Heath
    -0.06
    (&$
    -0.05
     \
    -0.05
    976
    -0.05
    Putin
    -0.05
    POSITIVE LOGITS
     Listed
    0.07
     McG
    0.07
    	MPI
    0.07
    .rgb
    0.06
     Talking
    0.06
     شد
    0.06
     Dış
    0.06
     think
    0.06
     захоп
    0.06
    .ObjectMeta
    0.06
    Act Density 0.120%

    No Known Activations