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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ninth
    -0.07
     Blood
    -0.07
     Yak
    -0.07
    onna
    -0.07
     MAV
    -0.07
     средства
    -0.07
     आ
    -0.07
    娘
    -0.07
     Order
    -0.07
     shooters
    -0.06
    POSITIVE LOGITS
    .erb
    0.06
     někter
    0.06
     grate
    0.06
     contacting
    0.06
    .isLoggedIn
    0.06
    _fonts
    0.06
    [train
    0.06
     rejecting
    0.06
    _abort
    0.06
    than
    0.06
    Act Density 0.006%

    No Known Activations