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

    Neuronpedia

    INDEX
    Explanations

    jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نع
    -0.07
    ीट
    -0.07
    rupt
    -0.06
    aud
    -0.06
     spun
    -0.06
     seguir
    -0.06
    _CMD
    -0.06
     oy
    -0.06
     avis
    -0.06
    (Seq
    -0.06
    POSITIVE LOGITS
    	Init
    0.07
    aviolet
    0.06
     deduct
    0.06
     Scripts
    0.06
    ToFile
    0.05
    _fail
    0.05
     Removal
    0.05
     تع
    0.05
     princip
    0.05
    ॉ
    0.05
    Act Density 0.009%

    No Known Activations