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

    Neuronpedia

    INDEX
    Explanations

    increased

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interior
    -0.08
    Snake
    -0.07
     remains
    -0.07
     totaled
    -0.07
     nood
    -0.07
     strang
    -0.07
     velocities
    -0.06
    mse
    -0.06
    ์ม
    -0.06
     listop
    -0.06
    POSITIVE LOGITS
    _seek
    0.07
    "]).
    0.06
    /copyleft
    0.06
    .KeyCode
    0.06
     Роз
    0.06
    ализи
    0.05
     Федера
    0.05
     fulfilling
    0.05
    =YES
    0.05
    /mobile
    0.05
    Act Density 0.036%

    No Known Activations