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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jaguar
    -0.07
     gradients
    -0.07
     JA
    -0.07
     Eagles
    -0.07
    624
    -0.07
    problems
    -0.06
     Forest
    -0.06
    (pack
    -0.06
     Sorting
    -0.06
     analogue
    -0.06
    POSITIVE LOGITS
    ीवन
    0.06
    ΕΥ
    0.06
     สม
    0.06
    ItemImage
    0.06
    _write
    0.06
    抬
    0.05
     standoff
    0.05
     jeunes
    0.05
    汽车
    0.05
    .qual
    0.05
    Act Density 0.017%

    No Known Activations