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

    Neuronpedia

    INDEX
    Explanations

    dissect that, feel safe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserModel
    0.54
     modeller
    0.48
    ケーション
    0.47
    Características
    0.47
    モデル
    0.46
     Heuer
    0.46
    modelo
    0.46
     untapped
    0.46
    구매
    0.46
    Тех
    0.45
    POSITIVE LOGITS
    oti
    0.50
    ick
    0.50
    oth
    0.49
    ards
    0.47
    ums
    0.46
     Consumption
    0.46
    sters
    0.46
    ongs
    0.46
    ensions
    0.46
    ard
    0.46
    Act Density 0.000%

    No Known Activations