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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zeitig
    -0.07
    近
    -0.06
     organs
    -0.06
     hned
    -0.06
     Ка
    -0.06
     aimed
    -0.06
     평균
    -0.06
     Jaguar
    -0.06
    eld
    -0.06
     diagrams
    -0.06
    POSITIVE LOGITS
    _COL
    0.06
     EOF
    0.06
     TEST
    0.06
    istrat
    0.06
     Leia
    0.06
     er
    0.06
    ♀♀
    0.06
    753
    0.06
    屏
    0.06
    mişti
    0.06
    Act Density 0.021%

    No Known Activations