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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HERE
    -0.08
    excerpt
    -0.07
    advertisement
    -0.07
    How
    -0.06
     cy
    -0.06
     mt
    -0.06
     PLEASE
    -0.06
    。↵↵↵↵↵↵
    -0.06
    伐
    -0.06
     eget
    -0.06
    POSITIVE LOGITS
     kron
    0.08
     Angels
    0.07
    اض
    0.07
     parted
    0.07
    婧
    0.07
    蔽
    0.07
    伦
    0.07
    _INCREF
    0.07
    باك
    0.07
     Swedish
    0.07
    Act Density 0.025%

    No Known Activations