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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest examining or assessing information

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

    look at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pysty
    -0.44
     poitrine
    -0.39
    :+:
    -0.34
     nød
    -0.33
     tarvit
    -0.32
    oredCriteria
    -0.32
     maux
    -0.31
     tričko
    -0.30
    kosť
    -0.29
     financieras
    -0.29
    POSITIVE LOGITS
    رشف
    0.69
    WriteTagHelper
    0.62
     Honours
    0.56
    URLException
    0.54
    oulos
    0.54
    ElementException
    0.53
    lisi
    0.52
    <unused52>
    0.52
    <unused23>
    0.52
    <unused8>
    0.52
    Act Density 0.005%

    No Known Activations