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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AE
    -0.06
    Multiplier
    -0.06
    OUNTER
    -0.06
    linewidth
    -0.06
    ai
    -0.06
     lunch
    -0.06
    �
    -0.06
     uplat
    -0.06
    ertoire
    -0.06
     IN
    -0.06
    POSITIVE LOGITS
    media
    0.07
    .Meta
    0.07
     بص
    0.06
    .Command
    0.06
     BITS
    0.06
    /Test
    0.06
     scientist
    0.06
    da
    0.06
    ٣
    0.06
    ,max
    0.06
    Act Density 0.454%

    No Known Activations