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

    Neuronpedia

    INDEX
    Explanations

    self-promotion or marketing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Probability
    -0.07
     Králové
    -0.07
    brahim
    -0.06
     amazed
    -0.06
    .Cluster
    -0.06
     Gy
    -0.06
     sat
    -0.06
     Humanities
    -0.06
    画
    -0.06
    _performance
    -0.06
    POSITIVE LOGITS
    .Cons
    0.07
    ยนต
    0.06
    ẳng
    0.06
     marketed
    0.06
     marketer
    0.06
    еної
    0.06
    ılmaktadır
    0.06
    marker
    0.06
     JNICALL
    0.06
    ắc
    0.06
    Act Density 0.032%

    No Known Activations