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

    Neuronpedia

    INDEX
    Explanations

    instances of common terms and pronouns that indicate quantity or participation

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

    most folks, anyway, A:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.66
     <>",
    -0.62
    WebElementEntity
    -0.57
    Vidite
    -0.51
     Administrativna
    -0.50
    ajevo
    -0.50
    oa̍t
    -0.49
    ValueStyle
    -0.49
    -0.48
    umán
    -0.46
    POSITIVE LOGITS
    Anyway
    0.47
     anyway
    0.46
     Anyway
    0.46
    .*")]
    0.42
    anyway
    0.40
    sella
    0.38
    wal
    0.38
    Parcelize
    0.36
    Vul
    0.36
    acco
    0.36
    Act Density 0.114%

    No Known Activations