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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಗರ
    -0.09
     वस्त
    -0.08
     aloud
    -0.08
     bounty
    -0.08
     wäert
    -0.08
     సంఘ
    -0.08
    ώντας
    -0.07
    301
    -0.07
     monopoly
    -0.07
    いっぱい
    -0.07
    POSITIVE LOGITS
    transpose
    0.09
     Identity
    0.09
     electrónica
    0.09
     transpose
    0.08
     matrices
    0.08
    .transpose
    0.08
     Bits
    0.08
    Matrices
    0.08
     matriz
    0.08
    Transpose
    0.08
    Act Density 0.004%

    No Known Activations