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

    Neuronpedia

    INDEX
    Explanations

    describing what this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.21
    ۔
    0.20
    ।
    0.20
    ።
    0.19
     जिससे
    0.18
    ；
    0.18
     ।
    0.17
     コン
    0.17
     (*
    0.17
     ("
    0.17
    POSITIVE LOGITS
     είναι
    0.26
     is
    0.25
     isn
    0.25
     seems
    0.23
    is
    0.23
     really
    0.23
     has
    0.22
     are
    0.22
     had
    0.21
     serves
    0.21
    Act Density 0.656%

    No Known Activations