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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ไลน
    -0.07
    andro
    -0.07
    ्यव
    -0.06
     Xm
    -0.06
     pickups
    -0.06
    ETYPE
    -0.06
     Mush
    -0.06
     "?
    -0.06
    Lng
    -0.06
    Sir
    -0.06
    POSITIVE LOGITS
     Fellow
    0.07
    .asarray
    0.07
    的小
    0.07
    alık
    0.07
    ้้
    0.06
    PLEASE
    0.06
    ía
    0.06
     rigid
    0.06
    Plug
    0.06
    cased
    0.06
    Act Density 0.044%

    No Known Activations