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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     typically
    -0.10
     essentially
    -0.08
     analysis
    -0.07
    _series
    -0.07
     организм
    -0.07
     offspring
    -0.07
     transmiss
    -0.07
    [w
    -0.07
    หลัก
    -0.07
     constants
    -0.07
    POSITIVE LOGITS
     novelist
    0.09
     Baumw
    0.09
     towering
    0.09
     futuristic
    0.09
     Tal
    0.08
    Buildings
    0.08
     Medieval
    0.08
    Portrait
    0.08
     тарихи
    0.08
     silhou
    0.08
    Act Density 0.007%

    No Known Activations