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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities involved in claims or rumors

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

    a verb followed by "it"

    np_acts-logits-general · gemini-2.0-flash

    it as a pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.85
     الحره
    -0.69
     صوتيه
    -0.64
     AssemblyCulture
    -0.63
    -------
    -0.62
    NOPQRST
    -0.61
    #
    -0.61
    RetentionPolicy
    -0.60
     doInBackground
    -0.59
    UVWXYZ
    -0.59
    POSITIVE LOGITS
     it
    2.90
    It
    1.86
     It
    1.77
    it
    1.67
    มัน
    1.15
    它
    1.08
     nó
    0.93
     آن
    0.92
     IT
    0.89
     มัน
    0.80
    Act Density 0.649%

    No Known Activations