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

    Neuronpedia

    INDEX
    Explanations

    specific references to legal cases and conditions related to discrimination and ownership within the context of a session or property management

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

    Non-English language text

    np_acts-logits-general · gemini-2.0-flash

    feminine third-person pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    -1.48
    himself
    -1.17
     his
    -1.14
    his
    -1.09
     Himself
    -1.05
     koji
    -1.02
    彼は
    -0.95
     који
    -0.90
     seine
    -0.90
    His
    -0.89
    POSITIVE LOGITS
     herself
    2.51
     she
    1.79
    herself
    1.73
     her
    1.71
    她
    1.25
     shes
    1.24
     그녀
    1.23
    但她
    1.22
    she
    1.21
     ihrem
    1.18
    Act Density 0.580%

    No Known Activations