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

    Neuronpedia

    INDEX
    Explanations

    provide food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اته
    0.74
    theit
    0.71
    targeted
    0.70
    δ
    0.67
     targeted
    0.66
    lieb
    0.65
     dels
    0.65
    ationen
    0.65
    ombic
    0.65
     bronchitis
    0.64
    POSITIVE LOGITS
     Фі
    0.90
    િંગ
    0.86
    cusson
    0.83
    いる
    0.81
     cualquiera
    0.80
    西亚
    0.80
    nikiem
    0.78
    Посилання
    0.78
     Thủ
    0.77
    䍩
    0.75
    Act Density 0.000%

    No Known Activations