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

    Neuronpedia

    INDEX
    Explanations

    news articles and blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ospace
    -0.31
    ponder
    -0.31
    wald
    -0.29
    cred
    -0.26
    reflect
    -0.25
    ibur
    -0.25
    ificent
    -0.25
    tre
    -0.25
    ordan
    -0.24
    everything
    -0.24
    POSITIVE LOGITS
    èĹĵ
    0.32
    Spark
    0.28
    åıĭ
    0.26
     pits
    0.26
    <?=
    0.26
    ürü
    0.26
     jobId
    0.25
    Job
    0.25
     advanced
    0.25
    åĩĭ
    0.24
    Act Density 0.003%

    No Known Activations