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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Satur
    -0.08
    无需
    -0.07
     kolej
    -0.07
     mercury
    -0.07
     distracted
    -0.07
    -Ass
    -0.07
    <Key
    -0.07
     När
    -0.07
     HOA
    -0.07
    Adapt
    -0.07
    POSITIVE LOGITS
     restantes
    0.10
    剩
    0.09
     dwind
    0.09
     restante
    0.09
     verble
    0.09
     remaining
    0.08
     leftover
    0.08
     inicio
    0.08
    .remaining
    0.08
    _remaining
    0.08
    Act Density 0.119%

    No Known Activations