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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming or code structure, specifically methods and stubs

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

    Well, followed by an observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.18
     snippetHide
    -0.91
    <unused41>
    -0.91
    [@BOS@]
    -0.91
    <unused68>
    -0.91
    <unused17>
    -0.91
    <unused51>
    -0.91
    <unused28>
    -0.91
    <unused8>
    -0.91
    <unused16>
    -0.91
    POSITIVE LOGITS
    3
    0.59
    1
    0.59
     
    0.58
    2
    0.56
    0
    0.56
    7
    0.52
    4
    0.52
    The
    0.51
    9
    0.51
    8
    0.51
    Act Density 0.001%

    No Known Activations