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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    environment
    -0.07
    修
    -0.07
    POINT
    -0.06
     extrad
    -0.06
    ▋▋
    -0.06
     レ
    -0.06
     userManager
    -0.06
     habitat
    -0.06
    _defaults
    -0.06
    _lift
    -0.06
    POSITIVE LOGITS
    заб
    0.07
    ้ผ
    0.06
     oath
    0.06
     محاس
    0.06
     fellows
    0.06
     Penis
    0.06
    *k
    0.06
    -copy
    0.06
     Δια
    0.05
    '/>
    0.05
    Act Density 0.004%

    No Known Activations