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

    Neuronpedia

    INDEX
    Explanations

    ending/eliminating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .normal
    -0.08
     माल
    -0.07
     reversed
    -0.07
    igkeiten
    -0.07
     груп
    -0.07
     서버
    -0.07
     side
    -0.07
    _regular
    -0.07
    正规的
    -0.07
    seit
    -0.07
    POSITIVE LOGITS
     scour
    0.09
     someday
    0.09
     obsession
    0.08
     relentlessly
    0.08
     collaboratively
    0.08
     abandonment
    0.08
     elusive
    0.08
     ambitions
    0.08
     american
    0.08
     strive
    0.08
    Act Density 0.028%

    No Known Activations