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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and aspiration

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

    Unusual punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    French writing and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …….
    -0.65
    …..
    -0.64
    </blockquote>
    -0.64
    ………
    -0.63
     appunto
    -0.63
    ,…
    -0.62
    ……..
    -0.62
     également
    -0.62
     moreover
    -0.61
     likewise
    -0.60
    POSITIVE LOGITS
    awtextra
    0.73
    Koordinaten
    0.68
     Fiche
    0.66
    ՚
    0.61
     definitely
    0.61
    dafx
    0.59
    ^(@)
    0.59
     enggak
    0.59
    ParallelGroup
    0.58
    ,’’
    0.58
    Act Density 0.209%

    No Known Activations