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

    Neuronpedia

    INDEX
    Explanations

    lifelong skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    0.50
    the
    0.48
    स्टिव
    0.47
    ako
    0.47
    woven
    0.46
    戦
    0.46
    umi
    0.46
    utos
    0.45
    腱
    0.45
    通用
    0.45
    POSITIVE LOGITS
     intéressante
    0.52
     religiosos
    0.51
     интерес
    0.50
     amico
    0.50
    }$:
    0.50
     linkCell
    0.49
     hostels
    0.49
    ItemsSource
    0.49
    мами
    0.49
     quaerat
    0.48
    Act Density 0.000%

    No Known Activations