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

    Neuronpedia

    INDEX
    Explanations

    volatile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     му
    -0.07
     문화
    -0.07
     Ferry
    -0.07
    (ob
    -0.07
    šen
    -0.06
     lonely
    -0.06
     मस
    -0.06
     되어
    -0.06
    osten
    -0.06
    980
    -0.06
    POSITIVE LOGITS
     subtotal
    0.06
    ві
    0.06
     Townsend
    0.06
    yonel
    0.06
    .Domain
    0.06
     amazingly
    0.06
    !↵↵↵
    0.05
     HTMLElement
    0.05
    solution
    0.05
    .student
    0.05
    Act Density 0.009%

    No Known Activations