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

    Neuronpedia

    INDEX
    Explanations

    steps forward in the process of solving a math problem, especially the word "next"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diffusion
    -0.08
     baiser
    -0.07
    Ĵáŀ
    -0.07
    oeff
    -0.06
    lder
    -0.06
    Å©
    -0.06
    wick
    -0.06
    ooke
    -0.06
    arih
    -0.06
     Uncategorized
    -0.06
    POSITIVE LOGITS
     next
    0.10
     then
    0.09
     Next
    0.09
    Next
    0.09
     To
    0.09
    为äºĨ
    0.08
    next
    0.07
    To
    0.07
     Then
    0.07
    .Next
    0.07
    Act Density 0.007%

    No Known Activations