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

    Neuronpedia

    INDEX
    Explanations

    coding-related syntax or structure in programming

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

    non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -1.15
     Administrativna
    -1.03
     resourceCulture
    -0.95
    iſchen
    -0.94
     kasarigan
    -0.93
     Biôgrafia
    -0.90
     Italijanski
    -0.88
    oa̍t
    -0.88
     ligiloj
    -0.88
    AISSEE
    -0.87
    POSITIVE LOGITS
     burbujas
    0.35
     ayrıca
    0.31
     secundario
    0.28
     nuages
    0.27
    reszcie
    0.27
     courants
    0.27
    1
    0.27
     palacio
    0.26
     agujas
    0.25
     velas
    0.25
    Act Density 0.001%

    No Known Activations