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

    Neuronpedia

    INDEX
    Explanations

    terms related to licensing and conditions in software documentation

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

    License.txt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.65
     ainfi
    -0.62
     ſei
    -0.60
     fread
    -0.59
    majánló
    -0.59
     ſelbſt
    -0.57
     './../
    -0.57
     queſta
    -0.56
     plufieurs
    -0.55
    ruguay
    -0.54
    POSITIVE LOGITS
    
    0.81
    
    0.70
    //
    0.56
     Highness
    0.56
    Personensuche
    0.54
    /**
    0.49
    /*
    0.49
     تضيفلها
    0.43
    <bos>
    0.40
     BrowserModule
    0.38
    Act Density 0.002%

    No Known Activations