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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the removal of substances or contaminants

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

    removing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.48
     IndexPath
    -0.41
     فريبيس
    -0.36
     behaviour
    -0.36
     behaviours
    -0.35
     strut
    -0.34
     אופ
    -0.34
    hésite
    -0.34
     useEffect
    -0.34
     association
    -0.34
    POSITIVE LOGITS
    exitRule
    0.65
    Removes
    0.63
     Removal
    0.60
    removal
    0.60
     removal
    0.59
    removing
    0.58
    Removal
    0.58
     Removes
    0.58
     removes
    0.57
     remover
    0.55
    Act Density 0.054%

    No Known Activations