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

    Neuronpedia

    INDEX
    Explanations

    targets and prey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    illez
    0.75
     ଜ
    0.75
     رہنے
    0.68
    xadmin
    0.67
    க்கல்
    0.66
     স্র
    0.66
    aların
    0.66
     ನಡುವ
    0.66
     afirma
    0.66
     rétro
    0.65
    POSITIVE LOGITS
     targets
    2.95
     target
    2.63
     Targets
    2.56
    targets
    2.54
    Targets
    2.42
     victims
    2.37
    target
    2.36
     prey
    2.34
     victim
    2.31
     Target
    2.27
    Act Density 0.446%

    No Known Activations