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

    Neuronpedia

    INDEX
    Explanations

    terms focused on specification and parameters

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

    to specify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    formik
    -0.41
    harvest
    -0.40
    🇷
    -0.37
    expiresIn
    -0.36
    Harvest
    -0.36
     Oberlin
    -0.35
     translateY
    -0.34
     utafitiHapana
    -0.33
     kern
    -0.33
    Relational
    -0.32
    POSITIVE LOGITS
     specified
    1.18
    specified
    1.10
     specify
    1.10
     Specified
    1.05
    Specify
    1.02
     Specify
    1.02
     specifies
    1.02
    Specified
    1.00
    指定
    1.00
    specify
    0.98
    Act Density 0.015%

    No Known Activations