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

    Neuronpedia

    INDEX
    Explanations

    DeepSpeed, Tensor Cores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सब्जियों
    0.46
     Penalty
    0.42
     verduras
    0.41
     Authentication
    0.41
     custodian
    0.40
    垂
    0.40
    嵃
    0.40
    蔬菜
    0.40
    Authentication
    0.39
     नु
    0.39
    POSITIVE LOGITS
    加速
    0.45
     Acceler
    0.43
    pit
    0.42
    acceler
    0.40
     accelerate
    0.40
     accelerating
    0.40
     Pit
    0.40
    Speed
    0.39
     aceler
    0.39
     pit
    0.39
    Act Density 0.003%

    No Known Activations