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

    Neuronpedia

    INDEX
    Explanations

    technical instructions related to data handling and querying

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

    your or project's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.75
    featureID
    -0.73
    ロウィン
    -0.73
    GOTREF
    -0.72
    ंदीखरीदारी
    -0.71
    VYMaps
    -0.71
    IndentedString
    -0.71
     surla
    -0.71
     mxArray
    -0.71
     الحره
    -0.71
    POSITIVE LOGITS
     your
    0.52
     yourself
    0.46
     yours
    0.44
     longer
    0.42
     YOUR
    0.39
     otherwise
    0.37
     analogous
    0.37
     steps
    0.36
    your
    0.36
     use
    0.36
    Act Density 0.054%

    No Known Activations