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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms associated with getter and setter methods in object-oriented programming

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

    Code, math, or legal text

    np_acts-logits-general · gemini-2.0-flash

    <start_of_turn> user or set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <em>
    -0.38
    <i>
    -0.37
    (
    -0.35
    <b>
    -0.34
     nicio
    -0.34
    while
    -0.33
    )))),
    -0.31
    知
    -0.31
    <eos>
    -0.30
    </tr>
    -0.30
    POSITIVE LOGITS
    <unused52>
    1.02
    <unused51>
    1.02
    <unused41>
    1.02
    <unused43>
    1.02
    <unused8>
    1.02
    [@BOS@]
    1.02
    <unused14>
    1.02
    <unused28>
    1.02
    <unused68>
    1.02
    <unused74>
    1.02
    Act Density 0.039%

    No Known Activations