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

    Neuronpedia

    INDEX
    Explanations

    pattern-seeking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     помощь
    0.48
     potencia
    0.47
     पोट
    0.46
    вание
    0.45
     configuração
    0.45
     lava
    0.44
     देती
    0.44
     weihn
    0.44
     зи
    0.44
    тение
    0.43
    POSITIVE LOGITS
     MEANS
    0.45
    াজনক
    0.44
    talk
    0.44
     Draft
    0.43
    是
    0.43
     Substances
    0.43
    1
    0.42
    season
    0.42
     Border
    0.42
    aneous
    0.42
    Act Density 0.005%

    No Known Activations