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

    Neuronpedia

    INDEX
    Explanations

    terminology related to the concept of "reversing" in various contexts

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

    reverse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seamnă
    -0.59
     culoare
    -0.56
     zwiſchen
    -0.55
    SizeMode
    -0.55
    niſſe
    -0.54
     picioare
    -0.54
    InputBorder
    -0.54
    الإنجليزية
    -0.54
    RuleContext
    -0.54
    ⟬
    -0.54
    POSITIVE LOGITS
     reverse
    1.32
     reversed
    1.18
     Reverse
    1.16
    Reverse
    1.09
    reverse
    1.06
    reversed
    1.00
     reverses
    0.96
     reversal
    0.93
    Reversed
    0.90
     reversing
    0.88
    Act Density 0.055%

    No Known Activations