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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indir
    -0.07
    ेल
    -0.06
    )))),
    -0.06
    ベル
    -0.06
     enraged
    -0.06
    τεύ
    -0.06
    
    -0.06
    createCommand
    -0.06
    "],["
    -0.06
    ै?
    -0.06
    POSITIVE LOGITS
     tn
    0.07
     PUBLIC
    0.06
     detrimental
    0.06
     허
    0.06
     Predator
    0.06
     quand
    0.06
     Dress
    0.06
    Diamond
    0.06
    �
    0.06
     Him
    0.06
    Act Density 0.016%

    No Known Activations