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

    Neuronpedia

    INDEX
    Explanations

    quantifiable measurements and concentrations typically used in scientific contexts

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

    percentages and money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idenav
    -0.50
    戬
    -0.48
    XmlAccessType
    -0.47
     Licence
    -0.45
    fung
    -0.43
    Personendaten
    -0.42
     Parame
    -0.42
    RegressionTest
    -0.41
    setVerticalGroup
    -0.41
    LOYEES
    -0.40
    POSITIVE LOGITS
     depending
    0.50
    aarrggbb
    0.46
    depending
    0.45
     whichever
    0.42
    ➋
    0.41
     vectorielles
    0.41
    IVEREF
    0.40
    Depending
    0.40
     $("<
    0.38
     $('<
    0.38
    Act Density 0.053%

    No Known Activations