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

    Neuronpedia

    INDEX
    Explanations

    follow up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.29
      
    0.29
    1
    0.26
    0.25
    2
    0.24
     *
    0.24
     `
    0.23
    .
    0.23
       
    0.23
    (
    0.23
    POSITIVE LOGITS
    <unused494>
    0.31
    <unused2176>
    0.31
     elytris
    0.30
    <unused260>
    0.30
     इजीली
    0.30
    <unused1882>
    0.30
    <unused573>
    0.29
    <unused1676>
    0.29
    <unused2022>
    0.29
    acağına
    0.29
    Act Density 0.001%

    No Known Activations