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

    Neuronpedia

    INDEX
    Explanations

    Navy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _initialize
    -0.07
    esc
    -0.06
    oral
    -0.06
    ereal
    -0.06
     物
    -0.06
     glamorous
    -0.06
    siblings
    -0.06
     окруж
    -0.06
    _kel
    -0.06
    aft
    -0.06
    POSITIVE LOGITS
     Navy
    0.22
     navy
    0.11
    <td
    0.08
    ㅋ
    0.07
    avy
    0.07
    líd
    0.07
     Checking
    0.06
     Kou
    0.06
    ΗΜΑ
    0.06
    _MATRIX
    0.06
    Act Density 0.002%

    No Known Activations