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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation in various contexts

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

    Punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niosek
    -0.69
     vectoriales
    -0.67
     الحره
    -0.67
     يتيمه
    -0.66
     članak
    -0.65
     quæ
    -0.64
    mybatisplus
    -0.63
     représ
    -0.62
     Houſe
    -0.61
     vettoriale
    -0.60
    POSITIVE LOGITS
     mal
    0.47
     stress
    0.47
    YNC
    0.46
     cry
    0.45
    inoj
    0.45
     pes
    0.44
     imb
    0.44
     pis
    0.43
     pho
    0.43
    نگ
    0.43
    Act Density 0.065%

    No Known Activations