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

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming or code-related elements

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

    g.command or s.add_dependency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.42
     (
    -0.32
    (
    -0.32
    ↵↵
    -0.30
     --
    -0.28
    ,
    -0.28
    ↵↵↵
    -0.27
     Niedersachsen
    -0.27
     mūsų
    -0.26
    ↵
    -0.26
    POSITIVE LOGITS
    <unused8>
    1.11
    <unused74>
    1.11
    <unused41>
    1.11
    <unused52>
    1.11
    <unused14>
    1.11
    <pad>
    1.11
    <unused16>
    1.11
    <unused28>
    1.10
    <unused23>
    1.10
    <unused3>
    1.10
    Act Density 0.007%

    No Known Activations