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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols

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

    Dollar sign ($) followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    mathematical punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -0.65
    </h5>
    -0.60
    </h3>
    -0.60
    .
    -0.55
     came
    -0.55
    </i>
    -0.55
     Die
    -0.54
    </blockquote>
    -0.53
    </strong>
    -0.52
     and
    -0.51
    POSITIVE LOGITS
     مشين
    1.08
     تانيه
    1.07
     Majefty
    0.97
     للمعارف
    0.94
     purpoſe
    0.93
     myſelf
    0.93
     насељу
    0.93
     reaſon
    0.92
     nahilalakip
    0.91
     Chwiliwch
    0.89
    Act Density 0.827%

    No Known Activations