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

    Neuronpedia

    INDEX
    Explanations

    pronouns and expressions that address the reader directly

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

    "You" followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    you can/should/may

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boîtier
    -0.44
     catég
    -0.40
    zzlement
    -0.39
     Investigaciones
    -0.37
     समीक्षाओं
    -0.37
     Meksi
    -0.37
     aimez
    -0.35
     indeks
    -0.35
    expandindo
    -0.35
    <?
    -0.35
    POSITIVE LOGITS
     can
    0.63
     needn
    0.54
     shouldn
    0.50
     nevoie
    0.48
     should
    0.47
     need
    0.47
    can
    0.47
     may
    0.46
     mustn
    0.46
     shouldnt
    0.45
    Act Density 0.208%

    No Known Activations