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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     context
    0.52
     contexts
    0.44
    anges
    0.42
    adequ
    0.42
     nativity
    0.41
    Context
    0.40
     contextual
    0.40
    CONTEXT
    0.40
    context
    0.40
     minimal
    0.40
    POSITIVE LOGITS
     uprav
    0.52
     Реги
    0.49
    ។
    0.49
     Тогда
    0.46
     Hlav
    0.46
     escrib
    0.45
     успі
    0.45
    ।
    0.45
     тех
    0.45
     فأ
    0.45
    Act Density 0.000%

    No Known Activations