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

    Neuronpedia

    INDEX
    Explanations

    cleaning, mildew, risks, error, currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    separatedBy
    0.52
     dissati
    0.49
     tentatives
    0.48
     Dawkins
    0.47
     detractors
    0.47
     familiarize
    0.47
     calamities
    0.47
     acquaint
    0.46
    ్రీన్
    0.46
     mathematicians
    0.46
    POSITIVE LOGITS
    </strong>
    0.48
    专业
    0.45
    실
    0.45
     podle
    0.44
    이
    0.44
    Comprehensive
    0.44
    Queue
    0.43
    élite
    0.43
    It
    0.43
    ched
    0.42
    Act Density 0.000%

    No Known Activations