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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _updates
    -0.08
     hasher
    -0.07
    _visit
    -0.07
     trả
    -0.06
     Biol
    -0.06
     нед
    -0.06
     phản
    -0.06
    \Notifications
    -0.06
     ongoing
    -0.06
     prer
    -0.06
    POSITIVE LOGITS
     Laur
    0.07
     Lens
    0.07
    _initializer
    0.07
    ClassLoader
    0.07
    Senior
    0.07
     Jeans
    0.06
     تغ
    0.06
    	set
    0.06
    半
    0.06
    Alias
    0.06
    Act Density 0.000%

    No Known Activations