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

    Neuronpedia

    INDEX
    Explanations

    patterns in structured data representations

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

    3 followed by $

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -1.07
     betweenstory
    -1.02
    <unused28>
    -0.94
    <unused3>
    -0.94
    <unused16>
    -0.94
    <unused41>
    -0.94
    <unused68>
    -0.94
    <unused14>
    -0.94
    [@BOS@]
    -0.94
    <unused8>
    -0.94
    POSITIVE LOGITS
    G
    0.32
     lentejuelas
    0.30
    W
    0.27
    <strong>
    0.26
    H
    0.25
    F
    0.25
    L
    0.24
    I
    0.23
    [
    0.23
     origines
    0.23
    Act Density 0.050%

    No Known Activations