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

    Neuronpedia

    INDEX
    Explanations

    verbs and action-related phrases indicating participation and involvement

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

    resigns, reunites, noted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.66
     ProtoMessage
    -0.62
    الحياه
    -0.57
     يتيمه
    -0.56
     autorytatywna
    -0.52
     GenerationType
    -0.51
     Administrativna
    -0.51
    principalTable
    -0.49
     препратки
    -0.45
    /**
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.49
     GetEnumerator
    0.45
    lccn
    0.45
    ことができました
    0.43
    的说道
    0.37
    劲
    0.37
    berdayakan
    0.37
     Inscrivez
    0.36
     mwenye
    0.36
    地说道
    0.36
    Act Density 0.051%

    No Known Activations