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

    Neuronpedia

    INDEX
    Explanations

    words related to the act of removing or reducing something

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

    eliminates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.47
     CanadaChoose
    -0.46
    addContainerGap
    -0.45
    uxxxx
    -0.44
    makeText
    -0.43
    WithIOException
    -0.43
    Autoritní
    -0.42
     flashing
    -0.42
     griff
    -0.41
    ｀*)
    -0.41
    POSITIVE LOGITS
     ilman
    0.64
    miyorum
    0.59
     neither
    0.55
     without
    0.50
    WITHOUT
    0.49
     sepenuhnya
    0.49
     żad
    0.48
     WITHOUT
    0.48
     tanpa
    0.48
     fără
    0.48
    Act Density 0.106%

    No Known Activations