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

    Neuronpedia

    INDEX
    Explanations

    insights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visceral
    -0.07
     Rad
    -0.06
     delivered
    -0.06
     helmets
    -0.06
    Sing
    -0.06
     determines
    -0.06
    ?)↵
    -0.06
    avl
    -0.06
    �
    -0.06
     сво
    -0.06
    POSITIVE LOGITS
     Cheap
    0.07
    _gp
    0.06
    asInstanceOf
    0.06
    (sigma
    0.06
     PSG
    0.06
     slump
    0.06
    GtkWidget
    0.06
    蛛
    0.06
     fracking
    0.06
    _quiz
    0.06
    Act Density 0.068%

    No Known Activations