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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Log
    -0.08
    Appro
    -0.06
    _SN
    -0.06
     Dude
    -0.06
    fur
    -0.06
    	want
    -0.06
    -mult
    -0.06
    ubes
    -0.06
     همان
    -0.06
    Syn
    -0.06
    POSITIVE LOGITS
    MASK
    0.08
    XX
    0.07
     queryParams
    0.06
    orThunk
    0.06
     云
    0.06
     им
    0.06
     emphasizes
    0.06
    ุตสาหกรรม
    0.06
     ثم
    0.06
    PYTHON
    0.06
    Act Density 0.003%

    No Known Activations