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

    Neuronpedia

    INDEX
    Explanations

    text related to personal interests and hobbies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "spare" or "made"

    np_acts-logits-general · gemini-2.0-flash

    outdoor hobbies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.74
    ReusableCell
    -0.66
    OGND
    -0.65
    LookAnd
    -0.57
    makeText
    -0.57
    قایناقلار
    -0.57
    AddTagHelper
    -0.56
    Composable
    -0.53
    قایناق‌لار
    -0.53
    Olvid
    -0.52
    POSITIVE LOGITS
    Outside
    0.94
     hobbies
    0.93
     Outside
    0.93
     outside
    0.92
     enjoys
    0.80
     OUTSIDE
    0.80
    outside
    0.76
     Hobbies
    0.75
     dehors
    0.72
    OUTSIDE
    0.72
    Act Density 0.089%

    No Known Activations