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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removal or uncovering of layers or defenses

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

    removed, unlocked, opened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rotación
    -0.45
     ivelany
    -0.45
    
    -0.45
    tagext
    -0.45
    ficulties
    -0.44
     '\\;'
    -0.43
     समीक्षाओं
    -0.43
     bénévoles
    -0.41
     certificación
    -0.41
     useSelector
    -0.40
    POSITIVE LOGITS
    unwrap
    0.44
     utafitiHapana
    0.44
     unlocked
    0.41
     opened
    0.40
     desblo
    0.39
     por
    0.38
     dAtA
    0.38
     revealed
    0.38
     unwra
    0.38
    removeClass
    0.36
    Act Density 0.216%

    No Known Activations