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

    Neuronpedia

    INDEX
    Explanations

    terms related to system availability and management metrics

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

    abstract technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Và
    -0.40
    rungsseite
    -0.40
     Pues
    -0.35
     christlichen
    -0.35
     giras
    -0.35
     ewigen
    -0.34
     Púb
    -0.34
     pertanto
    -0.33
     Zweiten
    -0.33
     pido
    -0.32
    POSITIVE LOGITS
     препратки
    0.76
    UMENT
    0.73
     monument
    0.73
    bourhood
    0.71
    agulation
    0.70
    piration
    0.70
    angelo
    0.69
    ྜ
    0.69
    arium
    0.68
    estine
    0.68
    Act Density 0.089%

    No Known Activations