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

    Neuronpedia

    INDEX
    Explanations

    terms related to adjustments and tuning mechanisms in various systems

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

    adjustments or tuning

    np_acts-logits-general · gemini-2.0-flash

    adjusted or tuned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.63
     OMITBAD
    -0.57
    EndContext
    -0.53
     Roskov
    -0.52
    elemField
    -0.52
    Diweddarwch
    -0.52
     المعيارى
    -0.51
    ImageContext
    -0.50
     Integrity
    -0.49
     transfieras
    -0.49
    POSITIVE LOGITS
     adjustment
    1.38
     adjusting
    1.27
     adjust
    1.27
     adjustments
    1.27
    調整
    1.17
     adjusts
    1.16
    Adjust
    1.12
     Adjusting
    1.10
     adjustable
    1.09
     adjusted
    1.08
    Act Density 0.945%

    No Known Activations