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

    Neuronpedia

    INDEX
    Explanations

    step numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यांना
    0.43
     Structures
    0.41
    Leaders
    0.40
    生死
    0.40
    前的
    0.40
     Перед
    0.40
     आणि
    0.39
     ஸ்த
    0.38
    賴
    0.38
    Antes
    0.38
    POSITIVE LOGITS
     වී
    0.45
     postId
    0.45
    oxel
    0.41
     midfield
    0.41
     midfielders
    0.40
     tuner
    0.40
     midfielder
    0.39
     paddock
    0.38
     horizontally
    0.38
    reflectionMap
    0.38
    Act Density 0.000%

    No Known Activations