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

    Neuronpedia

    INDEX
    Explanations

    elements related to decision-making and filtering processes

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    verbs after prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.48
    帖最后由
    -0.46
    endpush
    -0.44
    uxxxx
    -0.44
     MainAxisSize
    -0.41
     surla
    -0.34
    tangentMode
    -0.33
    Tud
    -0.33
     MMR
    -0.33
    stdc
    -0.33
    POSITIVE LOGITS
     nonUne
    0.52
     AssemblyTitle
    0.48
     pamamagitan
    0.47
     disambiguazione
    0.47
    TagMode
    0.46
     kuin
    0.46
     Bewußt
    0.45
     kebaikan
    0.44
     Theile
    0.44
     breiten
    0.44
    Act Density 0.763%

    No Known Activations