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

    Neuronpedia

    INDEX
    Explanations

    Matching algorithms and game theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corona
    -0.09
    ás
    -0.08
    네
    -0.08
     előtt
    -0.07
    emas
    -0.07
    کٹ
    -0.07
     кад
    -0.07
     elemento
    -0.07
    _CHILD
    -0.07
    كس
    -0.07
    POSITIVE LOGITS
    /preferences
    0.15
     preferences
    0.14
    preferences
    0.13
    _preferences
    0.13
     Preferences
    0.12
     preference
    0.12
    Preferences
    0.11
     preferencias
    0.11
     cravings
    0.11
    .preferences
    0.11
    Act Density 0.012%

    No Known Activations