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

    Neuronpedia

    INDEX
    Explanations

    instances of negative numbers or references to negativity

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

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.38
     jadx
    -0.35
    SOUNDBITE
    -0.34
    osaurs
    -0.33
     malades
    -0.33
     menim
    -0.32
    nextSibling
    -0.32
     along
    -0.31
    ECONDS
    -0.31
    GMENT
    -0.30
    POSITIVE LOGITS
    SourceChecksum
    0.75
    :✨
    0.74
     Roskov
    0.60
    IndentedString
    0.55
    GraphicsUnit
    0.54
    цездатний
    0.52
     lenker
    0.50
    abestanden
    0.50
    Vidite
    0.50
     alpes
    0.49
    Act Density 0.012%

    No Known Activations