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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or surprise in conversations

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

    asking "really?" or "seriously?"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.43
    ContextHolder
    -0.39
    rlpool
    -0.39
    UnusedPrivate
    -0.38
    iedenis
    -0.38
    TestTools
    -0.36
     rooms
    -0.36
    twimg
    -0.36
     balustra
    -0.35
    Enllaços
    -0.35
    POSITIVE LOGITS
    exitRule
    0.51
    MigrationBuilder
    0.48
     poveznice
    0.46
    Diweddarwch
    0.44
    FailureListener
    0.43
     متعلقه
    0.42
    UrlResolution
    0.41
     Komponist
    0.41
     xmlns
    0.41
    嘩
    0.40
    Act Density 0.046%

    No Known Activations