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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

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

    home health nurses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ast
    -0.42
     reaction
    -0.42
     nhật
    -0.38
     enca
    -0.38
     react
    -0.38
     hin
    -0.38
     protoimpl
    -0.36
     reag
    -0.36
     tibet
    -0.36
    Des
    -0.35
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.53
     immerhin
    0.52
    addContainerGap
    0.51
    complexContent
    0.46
    addGap
    0.46
    }}],
    0.44
    $}}
    0.44
     الرياضيه
    0.44
     lembran
    0.43
     bahagia
    0.42
    Act Density 0.002%

    No Known Activations