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

    Neuronpedia

    INDEX
    Explanations

    defining 'is just'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вання
    0.51
    ρό
    0.50
    رمی
    0.48
     белги
    0.48
    μή
    0.48
     recordó
    0.48
    тному
    0.48
     attén
    0.46
     imagina
    0.46
    нт
    0.46
    POSITIVE LOGITS
    bg
    0.44
    ج
    0.43
    ล
    0.42
    Die
    0.41
     pula
    0.41
    )',
    0.40
    histor
    0.40
    b
    0.40
     Tissue
    0.39
    '$,
    0.39
    Act Density 0.000%

    No Known Activations