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

    Neuronpedia

    INDEX
    Explanations

    omial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attach
    -0.09
    solutions
    -0.08
     totale
    -0.08
    _assign
    -0.08
    polar
    -0.08
    Total
    -0.08
    -0.08
    assign
    -0.08
     Total
    -0.08
     assignments
    -0.07
    POSITIVE LOGITS
     риск
    0.09
     pesan
    0.09
     безопас
    0.09
     здоровье
    0.09
     producto
    0.08
     龙
    0.08
     lanz
    0.08
     содержание
    0.08
    Toen
    0.08
    ството
    0.08
    Act Density 0.010%
    No Known Activations