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

    Neuronpedia

    INDEX
    Explanations

    step by step instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Step
    0.64
    ステップ
    0.59
    STEP
    0.58
     Step
    0.57
    step
    0.51
     step
    0.49
     STEP
    0.48
    stepping
    0.46
    步
    0.45
    Steps
    0.45
    POSITIVE LOGITS
    versal
    0.46
     deviation
    0.46
    জন্য
    0.42
     detailed
    0.40
    অতি
    0.39
     anlay
    0.39
    жду
    0.38
     verso
    0.38
    ಚ
    0.38
     Cómo
    0.38
    Act Density 0.002%

    No Known Activations