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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing frequency or abundance

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

    so followed by degree or frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.52
    rinfo
    -0.50
     lizenzfreies
    -0.46
    RefNanny
    -0.43
    ఔ
    -0.42
    hubanes
    -0.40
    逅
    -0.40
    MessageTagHelper
    -0.39
    oia
    -0.39
     otomatig
    -0.39
    POSITIVE LOGITS
     столь
    0.48
    这么多
    0.47
     tantos
    0.46
    AndEndTag
    0.45
    那么多
    0.43
    endmodule
    0.43
     tantas
    0.43
     inför
    0.42
     so
    0.41
    こんなに
    0.41
    Act Density 0.038%

    No Known Activations