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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications or instructions

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

    "In" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    prepositional phrases starting with "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.43
    Skocz
    -0.41
    (
    -0.40
     was
    -0.39
    re
    -0.36
    ish
    -0.35
    ↵↵
    -0.35
     did
    -0.35
     met
    -0.34
    帶
    -0.34
    POSITIVE LOGITS
     MainAxisSize
    1.03
    findpost
    1.02
    脚注の使い方
    0.95
    tvguidetime
    0.93
    Portale
    0.92
     مرئيه
    0.88
    StoryboardSegue
    0.87
    VersionUID
    0.87
    HtmlAttribute
    0.84
     Normdatei
    0.80
    Act Density 0.065%

    No Known Activations