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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy and temperature in scientific contexts

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

    zero energy, mean, derivative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.60
    AsUp
    -0.57
     ujednoznacz
    -0.53
     فريبيس
    -0.52
     unknownFields
    -0.50
    gebob
    -0.49
    monger
    -0.48
     mergeFrom
    -0.48
    idenav
    -0.47
    saraba
    -0.46
    POSITIVE LOGITS
     Zero
    1.13
     zero
    1.10
    Zero
    1.09
    zero
    1.02
     ZERO
    0.92
    ZERO
    0.88
     zéro
    0.84
    ゼロ
    0.82
    zeros
    0.78
     zeros
    0.69
    Act Density 0.043%

    No Known Activations