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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     precautions
    -0.06
     affair
    -0.06
    _updated
    -0.06
     Decoder
    -0.06
    TOOLS
    -0.06
     Trick
    -0.06
     Salem
    -0.06
    .pp
    -0.06
     возмож
    -0.06
    senal
    -0.06
    POSITIVE LOGITS
    UCH
    0.06
    ừng
    0.06
     architekt
    0.06
    ΕΤ
    0.06
    ーン
    0.06
    وب
    0.06
    たし
    0.06
    -ranking
    0.06
     richt
    0.06
    frontend
    0.06
    Act Density 0.007%

    No Known Activations