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

    Neuronpedia

    INDEX
    Explanations

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shows
    -0.07
    Foreground
    -0.06
    .market
    -0.06
     EQUI
    -0.06
     wegen
    -0.06
     обмеж
    -0.06
     iface
    -0.06
     contre
    -0.06
     hva
    -0.06
     pier
    -0.06
    POSITIVE LOGITS
    _directory
    0.08
    ρία
    0.07
    lion
    0.06
    ycled
    0.06
    IMARY
    0.06
     приклад
    0.06
    _FAST
    0.06
     препараты
    0.06
    quia
    0.06
    Emma
    0.06
    Act Density 0.014%

    No Known Activations