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

    Neuronpedia

    INDEX
    Explanations

    sentences that express opposition to a previous claim

    oai_token-act-pair · gemini-2.0-flash

    But

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.71
    sizeCache
    -0.63
    oredCriteria
    -0.62
    twimg
    -0.58
    StructEnd
    -0.58
    contentLoaded
    -0.57
     morire
    -0.57
    httphttps
    -0.56
     stället
    -0.56
    saraba
    -0.55
    POSITIVE LOGITS
    niająca
    0.47
    ::::::::
    0.45
    UnusedPrivate
    0.45
    AppendLine
    0.42
     veter
    0.42
    czema
    0.41
    त्रा
    0.41
    }:{
    0.41
     Kipling
    0.41
     calves
    0.40
    Act Density 0.594%

    No Known Activations