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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical and biological processes, focusing on frequency, characteristics, and strategies

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

    change through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -1.03
    <unused8>
    -1.02
    <unused43>
    -1.02
    <unused79>
    -1.02
    <unused14>
    -1.02
    [@BOS@]
    -1.02
    <unused23>
    -1.02
    <unused47>
    -1.02
    <unused3>
    -1.02
    <unused16>
    -1.02
    POSITIVE LOGITS
     Stirn
    0.28
    ,
    0.27
     is
    0.24
        
    0.23
      
    0.22
     Utilizamos
    0.22
    <eos>
    0.21
       
    0.21
     he
    0.20
     I
    0.20
    Act Density 0.276%

    No Known Activations