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

    Neuronpedia

    INDEX
    Explanations

    military support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inde
    -0.07
    WOOD
    -0.06
    _exceptions
    -0.06
     Dist
    -0.06
    สาร
    -0.06
     [%
    -0.06
     statute
    -0.06
    amiento
    -0.06
    endas
    -0.06
    [offset
    -0.06
    POSITIVE LOGITS
     Herrera
    0.06
     압
    0.06
     Wonderful
    0.06
     inert
    0.06
    +E
    0.06
    ืน
    0.06
    强
    0.06
    φυ
    0.06
    .elapsed
    0.06
    ภายใน
    0.06
    Act Density 0.030%

    No Known Activations