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

    Neuronpedia

    INDEX
    Explanations

    parent followed by helpline or parenthetical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     granddaughters
    0.47
    pla
    0.45
    ه
    0.43
     positioned
    0.42
     estadísticas
    0.42
     Geschä
    0.41
     ინტერ
    0.41
    ース
    0.41
    ول
    0.40
    PLOY
    0.40
    POSITIVE LOGITS
     Parent
    0.88
     parent
    0.80
    hetical
    0.79
    heses
    0.75
    Parent
    0.75
     Parental
    0.74
    hetically
    0.71
     parental
    0.70
     Paren
    0.69
    parent
    0.68
    Act Density 0.008%

    No Known Activations