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

    Neuronpedia

    INDEX
    Explanations

    representing teams or candidates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onic
    0.42
    Managed
    0.41
     Partly
    0.40
     Managed
    0.40
     разбира
    0.39
     справ
    0.38
     দুদ
    0.38
    seekers
    0.38
    Send
    0.38
    חו
    0.38
    POSITIVE LOGITS
     behalf
    0.70
     representing
    0.69
     colors
    0.64
     representando
    0.64
     represent
    0.63
     составе
    0.62
     belonging
    0.59
    representing
    0.59
     Colors
    0.58
     colours
    0.58
    Act Density 0.017%

    No Known Activations