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

    Neuronpedia

    INDEX
    Explanations

    markdown headers and formatting indicators

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

    HTML formatting tags

    np_acts-logits-general · gemini-2.0-flash

    section introductions and headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.84
     ویکی‌پدیا
    -0.71
    MockBean
    -0.69
    ResumeLayout
    -0.67
    BagLayout
    -0.65
     FetchType
    -0.64
     Signalez
    -0.62
     CascadeType
    -0.61
     Meksiku
    -0.58
     JpaRepository
    -0.57
    POSITIVE LOGITS
    What
    0.74
     What
    0.72
    what
    0.66
     what
    0.65
    Why
    0.65
     Why
    0.63
     why
    0.63
    why
    0.59
     WHAT
    0.58
    How
    0.57
    Act Density 0.084%

    No Known Activations