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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive adjectives indicating relationships or ownership

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

    Possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    possessive determiners and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    routeProvider
    -0.76
    DockStyle
    -0.65
     varandra
    -0.55
    ViewFeatures
    -0.54
     paljon
    -0.51
     enkelte
    -0.51
     respectivamente
    -0.51
    stateProvider
    -0.50
     dolgo
    -0.50
    tvguidetime
    -0.49
    POSITIVE LOGITS
     only
    0.79
     goal
    0.79
    jstor
    0.70
     مشين
    0.69
     DbType
    0.68
    身上
    0.67
     únicas
    0.67
     únicos
    0.67
     focus
    0.67
     aim
    0.67
    Act Density 0.222%

    No Known Activations