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

    Neuronpedia

    INDEX
    Explanations

    conversational exchanges and discussions about various topics

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

    performative verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.48
    SourceChecksum
    -0.38
    VersionUID
    -0.38
    MessageState
    -0.38
    ioutil
    -0.35
     pistola
    -0.35
     ImGui
    -0.35
    tagext
    -0.33
     CreateTagHelper
    -0.32
     समीक्षक
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.70
    0.69
    +#+
    0.59
     ProtoMessage
    0.52
     resourceCulture
    0.51
     lenker
    0.47
     estekak
    0.47
     beginnetje
    0.46
    ьаж
    0.44
     pierdas
    0.44
    Act Density 0.139%

    No Known Activations