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

    Neuronpedia

    INDEX
    Explanations

    what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused38>
    0.46
     "?"]
    0.42
    <unused7>
    0.42
    ടന
    0.42
     ഉപ
    0.41
     നിങ്ങളുടെ
    0.40
     ماحول
    0.40
     検
    0.39
    bindingFields
    0.38
     infotainment
    0.38
    POSITIVE LOGITS
     R
    0.43
     Nc
    0.43
     figure
    0.40
     ad
    0.39
     index
    0.39
     tide
    0.38
     NAS
    0.37
     port
    0.37
    +
    0.37
    NCR
    0.36
    Act Density 0.001%

    No Known Activations