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

    Neuronpedia

    INDEX
    Explanations

    syntax related to mathematical expressions and notation

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

    End of turn marker

    np_acts-logits-general · gemini-2.0-flash

    end of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    -0.35
    2
    -0.31
    3
    -0.31
    4
    -0.27
    0
    -0.27
    F
    -0.27
    if
    -0.25
    7
    -0.25
    9
    -0.25
    S
    -0.25
    POSITIVE LOGITS
    <end_of_turn>
    1.33
    <unused3>
    1.31
    <unused14>
    1.31
    <unused23>
    1.31
    <unused28>
    1.31
    [@BOS@]
    1.31
    <unused8>
    1.31
    <unused19>
    1.31
    <unused41>
    1.31
    <unused16>
    1.31
    Act Density 0.925%

    No Known Activations