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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related commands and dependencies

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

    context for code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.90
    DockStyle
    -0.82
     laſſen
    -0.81
     propOrder
    -0.76
    iſchen
    -0.75
    -0.74
     verſch
    -0.73
    <unused16>
    -0.72
    <unused14>
    -0.72
    <pad>
    -0.72
    POSITIVE LOGITS
     vejo
    0.28
     rzecz
    0.28
     verständ
    0.28
    abord
    0.27
     البر
    0.26
    Base
    0.26
    space
    0.26
    Première
    0.26
     işte
    0.25
    ,
    0.25
    Act Density 0.003%

    No Known Activations