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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate examples or instances

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

    specific examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.81
     snippetHide
    -0.77
     désolés
    -0.71
    ">//
    -0.70
    Personendaten
    -0.69
    ंदीखरीदारी
    -0.69
    complexContent
    -0.69
    SourceChecksum
    -0.68
     estekak
    -0.65
     ProtoMessage
    -0.65
    POSITIVE LOGITS
    otides
    0.40
    stuffs
    0.36
     tourné
    0.33
     Crooked
    0.33
     prób
    0.33
    ppuden
    0.33
     yoktur
    0.33
    もなく
    0.32
    Tome
    0.32
    ductory
    0.31
    Act Density 0.381%

    No Known Activations