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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or statistics

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

    97

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Robb
    -0.45
     iprot
    -0.41
     Bork
    -0.41
     ROBINSON
    -0.40
     Robinson
    -0.40
     abusing
    -0.39
     Rolf
    -0.39
     navbar
    -0.39
     Bullock
    -0.38
    ListGroup
    -0.38
    POSITIVE LOGITS
    ymce
    0.67
    IntoConstraints
    0.58
    RegressionTest
    0.54
    parsedMessage
    0.52
    timewa
    0.51
    LEncoder
    0.50
     فريبيس
    0.48
    msgTypes
    0.47
    Mutability
    0.47
     AudioClip
    0.46
    Act Density 0.037%

    No Known Activations