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

    Neuronpedia

    INDEX
    Explanations

    Layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dilig
    -0.08
     trembling
    -0.08
     pesticides
    -0.08
     transcripts
    -0.08
     reckless
    -0.07
     transición
    -0.07
     α
    -0.07
     stalking
    -0.07
    َي
    -0.07
     peaches
    -0.07
    POSITIVE LOGITS
     размещ
    0.08
     Toe
    0.08
     горизонт
    0.08
     вертик
    0.08
     сеп
    0.08
    bein
    0.08
     пуст
    0.08
    agte
    0.08
     Ап
    0.08
     lagt
    0.08
    Act Density 0.001%

    No Known Activations