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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preg
    -0.08
    ---------
    -0.07
    PageIndex
    -0.07
    /pay
    -0.07
    gd
    -0.07
    /rand
    -0.06
    bben
    -0.06
     parental
    -0.06
    ziel
    -0.06
    %%%%%%%%
    -0.06
    POSITIVE LOGITS
    UID
    0.06
    (Layout
    0.06
    '),
    0.06
     крем
    0.06
    énom
    0.06
     Вид
    0.06
    /display
    0.06
    _activity
    0.06
    (N
    0.06
    _signal
    0.05
    Act Density 0.005%

    No Known Activations