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

    Neuronpedia

    INDEX
    Explanations

    optional, possibly, additional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guerras
    0.47
    ExternalTaskPojo
    0.46
    FindingsRequest
    0.44
     französ
    0.43
    JScripts
    0.43
     महाराजा
    0.41
     berühm
    0.41
     histó
    0.40
    staaten
    0.40
    १८४
    0.40
    POSITIVE LOGITS
     optionally
    1.13
     Optionally
    0.92
     éventuellement
    0.77
     optional
    0.77
     possibly
    0.76
     additionally
    0.75
     additional
    0.73
     Possibly
    0.73
     Optional
    0.73
     maybe
    0.69
    Act Density 0.173%

    No Known Activations