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

    Neuronpedia

    INDEX
    Explanations

    terms related to components and processes in electronics and materials science

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

    reflexive pronouns and self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.55
    fitrión
    -0.52
    yntaxException
    -0.48
     <>",
    -0.45
    CppMethod
    -0.44
     GreatSchools
    -0.44
    UnknownFieldSet
    -0.43
    ArgsConstructor
    -0.43
     calendriers
    -0.42
     Canadian
    -0.41
    POSITIVE LOGITS
     itself
    0.62
    EndContext
    0.52
    itself
    0.51
     herself
    0.50
    自体は
    0.48
     themselves
    0.48
    本人
    0.47
    本身
    0.45
     themſelves
    0.45
    本体
    0.43
    Act Density 0.090%

    No Known Activations