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

    Neuronpedia

    INDEX
    Explanations

    reading integer input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tracked
    -0.09
    chestr
    -0.08
    astar
    -0.08
     Airways
    -0.08
     appreciating
    -0.08
    youtu
    -0.08
     fuerzas
    -0.08
    gradable
    -0.08
     maquinaria
    -0.08
     appreciate
    -0.08
    POSITIVE LOGITS
     Motiv
    0.08
     alk
    0.08
     ప్రయత్న
    0.08
     promising
    0.08
     తన
    0.08
    _candidate
    0.07
     Attempt
    0.07
     Motivation
    0.07
     ارسال
    0.07
     postings
    0.07
    Act Density 0.006%

    No Known Activations