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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explanations
    -0.06
    KW
    -0.06
    (stream
    -0.06
    Backup
    -0.06
     könnte
    -0.06
    628
    -0.06
    .rotation
    -0.06
     Fun
    -0.05
    project
    -0.05
     precio
    -0.05
    POSITIVE LOGITS
     аж
    0.07
    _Order
    0.07
     Kobe
    0.06
     protested
    0.06
    یه
    0.06
     الکترون
    0.06
    isContained
    0.06
    removeClass
    0.06
    .Site
    0.06
    ICIAL
    0.06
    Act Density 0.037%

    No Known Activations