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

    Neuronpedia

    INDEX
    Explanations

    consequences of non-compliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     syscall
    -0.07
    *np
    -0.07
     lep
    -0.06
     hơn
    -0.06
    他们
    -0.06
     confirmation
    -0.06
    .style
    -0.06
    ازات
    -0.06
    ernel
    -0.06
    .call
    -0.06
    POSITIVE LOGITS
    国際
    0.07
    _fmt
    0.06
    Bill
    0.06
    त
    0.06
    νια
    0.06
     athletics
    0.06
     Ideas
    0.06
     monitor
    0.06
    oubles
    0.06
     USDA
    0.06
    Act Density 0.039%

    No Known Activations