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

    Neuronpedia

    INDEX
    Explanations

    position zero or axis zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zeros
    0.52
     zeroes
    0.52
    Zeros
    0.52
    zeros
    0.48
     vanish
    0.43
     ০১
    0.43
     millions
    0.40
     zero
    0.39
    ゼロ
    0.39
     tens
    0.39
    POSITIVE LOGITS
     beth
    0.44
    最多的
    0.40
     zeroth
    0.39
     Wisdom
    0.38
     kle
    0.38
     включают
    0.38
     insurers
    0.37
    THR
    0.37
    编号
    0.37
     Insurance
    0.36
    Act Density 0.036%

    No Known Activations