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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lsp
    -0.07
     dbs
    -0.06
    (tb
    -0.06
     setters
    -0.06
     /^(
    -0.06
    te
    -0.06
    ń
    -0.06
    forcer
    -0.06
     )↵↵↵↵↵↵↵↵
    -0.06
    (bb
    -0.06
    POSITIVE LOGITS
    소
    0.07
     hints
    0.06
    产业
    0.06
    economic
    0.06
    ประม
    0.06
    Proposal
    0.06
    τωση
    0.06
    .setAction
    0.06
    usted
    0.06
     Περι
    0.06
    Act Density 0.011%

    No Known Activations