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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    افظ
    -0.07
     Canc
    -0.07
     defeat
    -0.06
     praises
    -0.06
     Screens
    -0.06
    ishment
    -0.06
    ponsive
    -0.06
    ôt
    -0.06
    991
    -0.06
    ERIC
    -0.06
    POSITIVE LOGITS
     서로
    0.07
     Ferry
    0.06
     yerine
    0.06
     runoff
    0.06
    にな
    0.06
     LNG
    0.06
     бач
    0.06
    \Data
    0.06
     Mata
    0.06
    leta
    0.06
    Act Density 0.039%

    No Known Activations