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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '?
    -0.07
     aggression
    -0.06
    .Button
    -0.06
    	Read
    -0.06
    perature
    -0.06
    赫
    -0.06
    че
    -0.06
    ्पर
    -0.06
    arkan
    -0.06
     sensation
    -0.06
    POSITIVE LOGITS
    |{↵
    0.07
     Nó
    0.06
    ��
    0.06
     commerc
    0.06
    )(__
    0.06
    .Transport
    0.06
     conson
    0.06
     booster
    0.06
    --)↵
    0.06
     Justice
    0.06
    Act Density 0.008%

    No Known Activations