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

    Neuronpedia

    INDEX
    Explanations

    arguments and rebuttals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SIM
    -0.08
    -0.08
     Nin
    -0.08
     ndër
    -0.07
    lel
    -0.07
     Extra
    -0.07
    GING
    -0.07
     Nim
    -0.07
    -extra
    -0.07
    签到
    -0.07
    POSITIVE LOGITS
    因此
    0.08
     עדיין
    0.08
     Descriptor
    0.08
     unaffected
    0.08
    _descriptor
    0.08
     argues
    0.08
     legitimately
    0.08
     Bordeaux
    0.08
    idae
    0.08
     stakeholders
    0.07
    Act Density 0.124%
    No Known Activations