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

    Neuronpedia

    INDEX
    Explanations

    Appeals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sf
    -0.07
    ')),
    -0.06
    δο
    -0.06
     sled
    -0.06
    Сам
    -0.06
    уг
    -0.06
    -trash
    -0.06
     příst
    -0.06
     дог
    -0.06
     nuru
    -0.06
    POSITIVE LOGITS
    Platforms
    0.08
     Portal
    0.07
     IPO
    0.07
    egrate
    0.06
    ivityManager
    0.06
    asmine
    0.06
     Conflict
    0.06
    alls
    0.06
     kits
    0.06
    scient
    0.06
    Act Density 0.002%

    No Known Activations