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

    Neuronpedia

    INDEX
    Explanations

    /copyleft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .П
    -0.07
    umba
    -0.07
     gaps
    -0.06
     quant
    -0.06
     reven
    -0.06
    oueur
    -0.06
     brink
    -0.06
     그림
    -0.06
     CHK
    -0.06
     โ
    -0.06
    POSITIVE LOGITS
    /copyleft
    0.09
    Greetings
    0.07
    .common
    0.06
    益
    0.06
    therapy
    0.06
    ／:
    0.06
    bable
    0.06
    lectron
    0.06
    .axis
    0.06
     ausge
    0.06
    Act Density 0.000%

    No Known Activations