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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating influence or causation

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

    influencing factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLR
    -0.60
    tvguidetime
    -0.59
     للاسماء
    -0.57
    Autoritní
    -0.56
    RTSC
    -0.51
    ImageField
    -0.50
    Життєпис
    -0.50
    uxxxx
    -0.50
    chestra
    -0.49
    basicConfig
    -0.48
    POSITIVE LOGITS
     frein
    0.37
    发表于
    0.35
    REASONS
    0.33
    /**
    0.33
    Gründe
    0.33
     reasons
    0.32
    Reasons
    0.32
    ünkü
    0.31
     knex
    0.31
     Reasons
    0.31
    Act Density 0.156%

    No Known Activations