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

    Neuronpedia

    INDEX
    Explanations

    intimate connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     εν
    0.73
     west
    0.69
     Engineers
    0.66
    )：
    0.64
     öst
    0.64
     inglese
    0.62
    ll
    0.60
    ्र
    0.57
     It
    0.57
    絭
    0.57
    POSITIVE LOGITS
    um
    0.77
    ٹے
    0.76
    e
    0.76
    ي
    0.76
     intimate
    0.75
    i
    0.75
     intimacy
    0.72
    intim
    0.71
    ে
    0.70
     ínt
    0.68
    Act Density 0.104%

    No Known Activations