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

    Neuronpedia

    INDEX
    Explanations

    references to children and family dynamics

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

    parental, kids, children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.62
     يتيمه
    -0.53
    <unused51>
    -0.52
    <unused42>
    -0.52
    <unused52>
    -0.52
    <unused23>
    -0.52
    <unused74>
    -0.52
    <unused79>
    -0.52
    <pad>
    -0.52
    [@BOS@]
    -0.52
    POSITIVE LOGITS
     parental
    0.38
    AddTagHelper
    0.37
     collectons
    0.36
    ransition
    0.35
    fromCharCode
    0.34
     cór
    0.33
     hasNext
    0.32
     kids
    0.31
     pediatrician
    0.31
     hijo
    0.30
    Act Density 0.047%

    No Known Activations