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

    Neuronpedia

    INDEX
    Explanations

    strings that resemble quotations or textual data formats

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

    Cannot find module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scepticism
    -0.50
     resourceCulture
    -0.47
     splendour
    -0.47
    Fibre
    -0.46
     sondern
    -0.46
    eavour
    -0.45
    coloured
    -0.45
     practised
    -0.45
    Licence
    -0.45
     honours
    -0.44
    POSITIVE LOGITS
    XmlAccessorType
    0.64
    cdnjs
    0.55
    NoSuchAlgorithm
    0.52
    ፩
    0.51
     يتيمه
    0.51
     QtWidgets
    0.50
     zijne
    0.50
    doPost
    0.49
    haviors
    0.47
    QMetaType
    0.46
    Act Density 0.033%

    No Known Activations