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

    Neuronpedia

    INDEX
    Explanations

    lists contributors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igmoid
    -0.06
    MH
    -0.06
     grocery
    -0.06
     EDT
    -0.06
    .transactions
    -0.06
    XmlAttribute
    -0.06
    iect
    -0.06
    )init
    -0.06
    andro
    -0.06
     Marina
    -0.06
    POSITIVE LOGITS
    雑
    0.07
     plag
    0.07
    creating
    0.06
    .instrument
    0.06
     Templates
    0.06
     Extension
    0.06
     المد
    0.06
    composed
    0.06
     coup
    0.06
     mutil
    0.06
    Act Density 0.010%

    No Known Activations