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

    Neuronpedia

    INDEX
    Explanations

    instances of perception and realization

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

    past tense and modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     holo
    -0.45
    Aholisi
    -0.45
     snippetHide
    -0.44
     polig
    -0.42
    tvguidetime
    -0.42
    الحياه
    -0.41
    litude
    -0.40
     Houſe
    -0.40
    Judgment
    -0.39
    تقاوى
    -0.39
    POSITIVE LOGITS
    دانشنامهٔ
    0.46
    UnusedPrivate
    0.46
    AnchorStyles
    0.44
    SharedCtor
    0.44
    новниш
    0.44
     spelers
    0.42
     giocatori
    0.42
     विश्वसनीयता
    0.41
    inigungs
    0.39
     tafel
    0.38
    Act Density 0.361%

    No Known Activations