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

    Neuronpedia

    INDEX
    Explanations

    decisions, sacrifices, arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Directed
    -0.07
    .Write
    -0.06
    Get
    -0.06
     آل
    -0.06
     aggravated
    -0.06
     Ethics
    -0.06
     Added
    -0.06
     тя
    -0.06
    forall
    -0.06
     take
    -0.06
    POSITIVE LOGITS
    atar
    0.07
    _LESS
    0.07
    .players
    0.07
     '=',
    0.07
    ۱۱
    0.06
     꿈
    0.06
    _LOGIN
    0.06
    	flex
    0.06
     petition
    0.06
    PAT
    0.06
    Act Density 0.097%

    No Known Activations