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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to software identity management

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

    identity and matrix concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ロウィン
    -0.83
    ſicht
    -0.82
    <unused43>
    -0.80
    <unused68>
    -0.80
    <unused41>
    -0.80
    <unused28>
    -0.80
    <unused16>
    -0.79
    <unused17>
    -0.79
    <unused14>
    -0.79
    [@BOS@]
    -0.79
    POSITIVE LOGITS
    Identity
    0.49
     identity
    0.47
    IDENTITY
    0.41
    identity
    0.41
     Identity
    0.38
    identité
    0.32
    ↵↵
    0.31
     
    0.31
    1
    0.30
     identité
    0.29
    Act Density 0.002%

    No Known Activations