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

    Neuronpedia

    INDEX
    Explanations

    say ]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     השימוש
    -0.07
    뭇
    -0.07
    Functional
    -0.06
    ALTH
    -0.06
    олод
    -0.06
    宅
    -0.06
    :init
    -0.06
    üs
    -0.06
    不让
    -0.06
    那個
    -0.06
    POSITIVE LOGITS
    חמש
    0.08
    .front
    0.07
     Wolff
    0.07
     blackjack
    0.07
    .disconnect
    0.07
     squeez
    0.07
    swap
    0.07
     Ballard
    0.07
    _GRANTED
    0.07
    גרמניה
    0.07
    Act Density 0.046%

    No Known Activations