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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <TSource
    -0.07
    (t
    -0.06
    .System
    -0.06
     Sys
    -0.06
     titulo
    -0.06
     datasource
    -0.06
    ροχή
    -0.06
     startDate
    -0.06
    gems
    -0.06
     німець
    -0.06
    POSITIVE LOGITS
    γκ
    0.07
    ใคร
    0.07
     आप
    0.07
    Px
    0.07
    48
    0.07
     Aware
    0.06
    plays
    0.06
    lain
    0.06
    ��态
    0.06
     अपन
    0.06
    Act Density 0.003%

    No Known Activations