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

    Neuronpedia

    INDEX
    Explanations

    words associated with scientific or mathematical concepts

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

    describing relationships between people

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns or related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.50
    ishan
    -0.50
    packages
    -0.46
    下一
    -0.45
    chtete
    -0.45
     pool
    -0.45
     all
    -0.43
     urmă
    -0.42
    ()]);
    -0.42
     All
    -0.42
    POSITIVE LOGITS
     yours
    0.88
    GEBURTSDATUM
    0.77
    ของคุณ
    0.76
    yours
    0.71
     hers
    0.69
     Yours
    0.68
    SharedCtor
    0.65
     ours
    0.64
     theirs
    0.64
    mybatisplus
    0.63
    Act Density 0.941%

    No Known Activations