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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prevalence or commonality

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

    most of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.75
    principalColumn
    -0.69
    AndEndTag
    -0.66
    bootstrapcdn
    -0.66
     CanadaChoose
    -0.62
    OGND
    -0.60
     transférez
    -0.59
     الرياضيه
    -0.59
    Hentet
    -0.58
     Италијани
    -0.58
    POSITIVE LOGITS
    ToAction
    0.38
    AppName
    0.35
     basura
    0.35
     toiminta
    0.34
     miseria
    0.34
     facilities
    0.33
     vuotta
    0.33
     aktiviteter
    0.33
     löytyy
    0.33
    คง
    0.33
    Act Density 0.058%

    No Known Activations