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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawberry
    0.31
    焓
    0.30
    merksamkeit
    0.28
     mutta
    0.28
    त्रेयी
    0.28
     terrasse
    0.27
     maladie
    0.27
     oiseaux
    0.27
    elevationMap
    0.27
    kloud
    0.26
    POSITIVE LOGITS
    event
    0.28
    -
    0.28
    {
    0.28
    _
    0.26
    &#
    0.26
    ↵↵↵
    0.26
    λ
    0.26
    v
    0.25
    當時
    0.25
    <em>
    0.25
    Act Density 0.044%

    No Known Activations