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

    Neuronpedia

    INDEX
    Explanations

    random data generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    btnLogin
    0.43
     усіх
    0.42
    greencar
    0.40
    ymoon
    0.39
     hormati
    0.39
    指摘
    0.38
    зре
    0.38
     महत्त्वा
    0.37
     njegova
    0.37
     retrouvé
    0.37
    POSITIVE LOGITS
     random
    1.33
     randomly
    1.24
    random
    1.12
    随机
    1.10
     Random
    1.08
    Random
    1.06
     randomize
    1.00
     randomness
    0.98
     generating
    0.92
     RANDOM
    0.91
    Act Density 0.564%

    No Known Activations