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

    Neuronpedia

    INDEX
    Explanations

    patterns involving contact information or phone numbers

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

    user messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.51
    AddTagHelper
    -0.48
    lccn
    -0.44
     seti
    -0.39
    PostInfinity
    -0.37
     láser
    -0.37
     uds
    -0.36
     gouvern
    -0.36
    setVerticalGroup
    -0.36
    HasAnnotation
    -0.36
    POSITIVE LOGITS
     صوتيه
    0.54
     IBOutlet
    0.54
    :✨
    0.54
    ressee
    0.49
    principalColumn
    0.49
     שוליים
    0.46
    IBOutlet
    0.45
    ymal
    0.45
    rzej
    0.44
    racite
    0.44
    Act Density 0.001%

    No Known Activations