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

    Neuronpedia

    INDEX
    Explanations

    sequences of quotation marks and related punctuation

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

    user inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.73
    SourceChecksum
    -0.63
     Taktlose
    -0.57
    Externé
    -0.56
    OGND
    -0.56
     חיצוניים
    -0.51
    LayoutStyle
    -0.50
    ⓧ
    -0.50
     esternos
    -0.49
    تقاوى
    -0.49
    POSITIVE LOGITS
     etc
    0.49
     vein
    0.41
     people
    0.40
     pets
    0.39
     stick
    0.39
     сти
    0.38
    etc
    0.37
     love
    0.37
     pet
    0.36
    urance
    0.36
    Act Density 0.006%

    No Known Activations