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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Utils
    -0.07
    ERA
    -0.07
    aku
    -0.07
     programmer
    -0.07
    andi
    -0.07
    tl
    -0.07
     Forest
    -0.06
    era
    -0.06
     TextInput
    -0.06
     หล
    -0.06
    POSITIVE LOGITS
     lạ
    0.06
    丰
    0.06
    Dur
    0.06
    _FLAGS
    0.06
    NESS
    0.06
     등의
    0.06
    ]*(
    0.06
     phot
    0.06
     markers
    0.06
    的是
    0.06
    Act Density 0.065%

    No Known Activations