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

    Neuronpedia

    INDEX
    Explanations

    synthesize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JP
    -0.09
     Confeder
    -0.09
     jp
    -0.07
     jubile
    -0.07
     लगाए
    -0.07
     دع
    -0.07
    �
    -0.07
    lji
    -0.07
     downfall
    -0.07
     ja
    -0.07
    POSITIVE LOGITS
    意见
    0.09
     �
    0.08
     actionable
    0.08
     Informationen
    0.08
    _information
    0.08
    551
    0.08
     المعلومات
    0.08
    'information
    0.07
     میان
    0.07
    'informations
    0.07
    Act Density 0.006%

    No Known Activations