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

    Neuronpedia

    INDEX
    Explanations

    numeric codes and phrases associated with eligibility criteria in official documents

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

    at least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.77
     queſta
    -0.75
    principalColumn
    -0.73
    ロウィン
    -0.70
    AndEndTag
    -0.69
     Houſe
    -0.69
     CreateTagHelper
    -0.69
     laſſen
    -0.67
    AddTagHelper
    -0.66
    Personensuche
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.36
    Nice
    0.33
     nice
    0.32
    θος
    0.31
    ↵
    0.31
     <<<<<<<<<<<<<<
    0.30
     detailed
    0.29
    पि
    0.28
    We
    0.28
    Oh
    0.27
    Act Density 0.020%

    No Known Activations