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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sources or references

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

    Following "according" with the word "to"

    np_acts-logits-general · gemini-2.0-flash

    according to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firebaseConfig
    -0.65
    ьаж
    -0.63
    StructEnd
    -0.63
     ogóle
    -0.61
    ambique
    -0.57
    secuencias
    -0.56
     connecté
    -0.52
     věci
    -0.52
    SourceChecksum
    -0.51
    Skocz
    -0.51
    POSITIVE LOGITS
     legend
    0.77
     recent
    0.64
     reports
    0.64
     him
    0.63
     tradition
    0.62
     rules
    0.61
     plan
    0.58
     schedule
    0.58
     their
    0.58
     instructions
    0.57
    Act Density 0.126%

    No Known Activations