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

    Neuronpedia

    INDEX
    Explanations

    black

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moderate
    -0.08
    _embeddings
    -0.07
    mant
    -0.07
     Advertisement
    -0.07
    唐
    -0.07
     birkaç
    -0.07
     selective
    -0.07
    .bundle
    -0.06
    .serial
    -0.06
    他也
    -0.06
    POSITIVE LOGITS
    cken
    0.08
    /class
    0.07
    눅
    0.07
     عليك
    0.07
    izin
    0.07
    科技创新
    0.07
    jure
    0.06
     Kia
    0.06
    .enqueue
    0.06
    莅
    0.06
    Act Density 0.042%

    No Known Activations