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

    Neuronpedia

    INDEX
    Explanations

    Writing and writers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рам
    -0.07
     달
    -0.07
     rval
    -0.06
    旋
    -0.06
    -largest
    -0.06
     reckon
    -0.06
     marching
    -0.06
     holdings
    -0.06
    _provider
    -0.06
    िद
    -0.06
    POSITIVE LOGITS
     dlouhodob
    0.07
     veya
    0.06
    ray
    0.06
    .createElement
    0.06
    oon
    0.06
     workout
    0.06
    했다
    0.06
    ILLISECONDS
    0.06
     června
    0.06
     entertaining
    0.06
    Act Density 0.046%

    No Known Activations