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

    Neuronpedia

    INDEX
    Explanations

    arousal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DriverManager
    -0.07
    piar
    -0.07
    DEPTH
    -0.07
    530
    -0.07
    capital
    -0.06
    .builder
    -0.06
     GridBagConstraints
    -0.06
    еко
    -0.06
     defiance
    -0.06
     doctrine
    -0.06
    POSITIVE LOGITS
     arousal
    0.07
    (proj
    0.07
     arous
    0.06
    /bl
    0.06
    …↵↵↵↵
    0.06
     Erdoğan
    0.06
     aroused
    0.06
     Carousel
    0.06
    //
↵
↵
    0.06
    /on
    0.06
    Act Density 0.005%

    No Known Activations