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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming terms

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.61
    oció
    -0.59
    hishek
    -0.56
    ::::::::
    -0.55
    DataSnapshot
    -0.54
    }")]
    -0.54
    ValuePair
    -0.52
    Hochspringen
    -0.50
    ├──
    -0.50
     quanh
    -0.50
    POSITIVE LOGITS
     препратки
    0.49
     onOptions
    0.47
    contentLoaded
    0.46
     discorso
    0.46
    
    0.45
     Dě
    0.45
    AddTagHelper
    0.45
     consape
    0.44
     Dès
    0.43
    fiez
    0.43
    Act Density 3.862%

    No Known Activations