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

    Neuronpedia

    INDEX
    Explanations

    take ownership or advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stop
    0.74
    aryng
    0.74
    STOP
    0.73
    oglob
    0.73
    нё
    0.69
    記載
    0.69
     způso
    0.69
    dail
    0.69
    tweet
    0.69
    Calend
    0.68
    POSITIVE LOGITS
     advantage
    2.46
    advantage
    1.81
     care
    1.68
     ventaja
    1.60
     avantage
    1.53
     pride
    1.48
     Advantage
    1.45
     advantages
    1.43
     precautions
    1.42
     liberties
    1.41
    Act Density 0.063%

    No Known Activations