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

    Neuronpedia

    INDEX
    Explanations

    avoidant attachment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     десяти
    0.43
    धारणा
    0.41
     spille
    0.40
     סי
    0.39
    ísima
    0.38
    ポット
    0.38
     यु
    0.38
     本
    0.37
     Bản
    0.37
    䀓
    0.36
    POSITIVE LOGITS
     high
    0.85
    high
    0.77
     low
    0.77
    High
    0.70
     высокий
    0.68
     High
    0.66
     высокая
    0.65
     высоким
    0.64
    の高
    0.64
    Low
    0.63
    Act Density 0.032%

    No Known Activations