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

    Neuronpedia

    INDEX
    Explanations

    Hall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    梅西
    -0.08
     sideways
    -0.07
     pequeño
    -0.07
     [+
    -0.07
     babe
    -0.06
    /Test
    -0.06
     Greenwich
    -0.06
    来回
    -0.06
    лекс
    -0.06
     aux
    -0.06
    POSITIVE LOGITS
    Interop
    0.07
    asia
    0.07
     pointer
    0.07
    apel
    0.07
    	version
    0.07
    パソ
    0.06
    有价值的
    0.06
     SCI
    0.06
    PO
    0.06
    ])-
    0.06
    Act Density 0.009%

    No Known Activations