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

    Neuronpedia

    INDEX
    Explanations

    letters, items, continuous, Sun, system, SST

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |
    0.43
    HEX
    0.42
     finland
    0.41
    P
    0.40
     version
    0.39
    や
    0.38
    eli
    0.38
    F
    0.38
     prior
    0.38
    constant
    0.38
    POSITIVE LOGITS
    ꔰ
    0.49
     многочис
    0.47
    𝑳
    0.46
     भीड़
    0.45
     noting
    0.45
     attentively
    0.45
    <unused2169>
    0.45
     অনেকটা
    0.44
    楾
    0.44
     มิ
    0.44
    Act Density 0.001%

    No Known Activations