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

    Neuronpedia

    INDEX
    Explanations

    methods for describing situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    0.49
     Absolutely
    0.41
     VI
    0.41
    [/
    0.41
     authoritarian
    0.40
     [.
    0.38
     inten
    0.38
     [/
    0.38
     max
    0.38
    {[
    0.38
    POSITIVE LOGITS
    ശാസ്ത്ര
    0.45
    杣
    0.44
    رسٹ
    0.42
    漅
    0.41
     nondestructive
    0.41
    ະລ
    0.40
    Bibliografia
    0.40
    fptr
    0.39
    SdkVersion
    0.39
    ਾਲ
    0.39
    Act Density 0.002%

    No Known Activations