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

    Neuronpedia

    INDEX
    Explanations

    negative commands or prohibitions related to editing or modifying content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    do not edit or alter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.57
     BorderSide
    -0.48
    RegressionTest
    -0.48
     sahibi
    -0.43
     člen
    -0.42
    KommentareTeilen
    -0.42
    ListItemIcon
    -0.42
     GenerationType
    -0.41
    masalahan
    -0.40
     jurado
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.52
    ">//
    0.51
    Derbyniad
    0.47
     Roskov
    0.43
     NÃO
    0.41
    NonUser
    0.41
     cherchés
    0.41
    tagHelperRunner
    0.39
    complexContent
    0.39
    ſelves
    0.39
    Act Density 0.001%

    No Known Activations