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

    Neuronpedia

    INDEX
    Explanations

    102

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _j
    -0.07
     Mission
    -0.07
     George
    -0.07
    ประว
    -0.07
    庄
    -0.07
     moyen
    -0.07
    _dot
    -0.07
     unf
    -0.07
     rotation
    -0.07
     wegen
    -0.06
    POSITIVE LOGITS
    102
    0.12
    نس
    0.07
    103
    0.07
    101
    0.07
    shaled
    0.07
    ASC
    0.06
    .HttpServletResponse
    0.06
    usto
    0.06
     текст
    0.06
    IMIZE
    0.06
    Act Density 0.010%

    No Known Activations