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

    Neuronpedia

    INDEX
    Explanations

    terms related to trade-offs and costs associated with choices or abilities

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

    trade-offs and contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Демографія
    -0.56
    ⓧ
    -0.54
    RTEX
    -0.52
     kasarigan
    -0.52
    $_['
    -0.51
     يتيمه
    -0.51
     ujednoznacz
    -0.51
    Personendaten
    -0.50
     للاسماء
    -0.49
    mybatisplus
    -0.49
    POSITIVE LOGITS
    nesc
    0.32
     bedien
    0.30
    uc
    0.29
    か
    0.29
    idom
    0.29
     olsa
    0.29
    それは
    0.29
    ณ
    0.28
    hyrchwyd
    0.28
     Buss
    0.28
    Act Density 0.061%

    No Known Activations