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

    Neuronpedia

    INDEX
    Explanations

    Theory of Planned Behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regulators
    -0.08
     Primera
    -0.08
    helpers
    -0.07
     altas
    -0.07
     frågor
    -0.07
     regulator
    -0.07
    _opts
    -0.07
     '/',
    -0.07
     themes
    -0.07
     besoins
    -0.07
    POSITIVE LOGITS
     outlook
    0.08
     ಕಟ್ಟ
    0.08
    lfriend
    0.08
     intelect
    0.08
     lich
    0.08
    춘
    0.08
     voorsp
    0.08
     Obi
    0.08
     outlaw
    0.07
    gwa
    0.07
    Act Density 0.001%

    No Known Activations