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

    Neuronpedia

    INDEX
    Explanations

    -select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     перем
    -0.06
     axle
    -0.06
    яс
    -0.06
     avg
    -0.06
    igor
    -0.06
     wxT
    -0.06
    analyze
    -0.06
     testcase
    -0.06
    <I
    -0.06
     present
    -0.06
    POSITIVE LOGITS
    务
    0.07
    ovaly
    0.07
    ент
    0.07
    ("$
    0.07
    .inc
    0.06
    ανδ
    0.06
    ----------
↵
    0.06
    .ar
    0.06
    aban
    0.06
    IID
    0.06
    Act Density 0.003%

    No Known Activations