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

    Neuronpedia

    INDEX
    Explanations

    kernel configuration or kicking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nets
    0.39
    ಷ್
    0.39
    馴染
    0.37
     benevolence
    0.37
    bugs
    0.36
     印
    0.36
    mard
    0.36
    inFile
    0.36
    ೂರ್
    0.36
    倒
    0.35
    POSITIVE LOGITS
     kicker
    0.62
     kicking
    0.60
     kicks
    0.51
     kick
    0.49
     kicked
    0.47
    踢
    0.47
     kickoff
    0.45
     penalized
    0.44
     points
    0.42
    Kick
    0.42
    Act Density 0.025%

    No Known Activations