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

    Neuronpedia

    INDEX
    Explanations

    references to financial metrics and legal judgments

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

    in honour of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.95
    ﹧
    -0.85
    <unused23>
    -0.84
    <unused41>
    -0.84
    <unused14>
    -0.84
    <unused51>
    -0.83
    <unused68>
    -0.83
    <unused17>
    -0.83
    <unused8>
    -0.83
    <unused3>
    -0.83
    POSITIVE LOGITS
    1
    0.37
    []
    0.36
     המע
    0.36
    -
    0.35
    ::
    0.35
    <eos>
    0.35
    dir
    0.34
    ↵↵
    0.34
    bes
    0.33
    2
    0.33
    Act Density 0.158%

    No Known Activations