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

    Neuronpedia

    INDEX
    Explanations

    advancement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helpless
    -0.08
    620
    -0.07
    Apart
    -0.07
     libertarian
    -0.06
     shoulders
    -0.06
    repository
    -0.06
     Playground
    -0.06
    nad
    -0.06
     passenger
    -0.06
    minimal
    -0.06
    POSITIVE LOGITS
     ELF
    0.07
     desea
    0.07
     بالإ
    0.06
    ующих
    0.06
     INTER
    0.06
     ethers
    0.06
     horny
    0.06
    _PROD
    0.06
    iyor
    0.06
     hvordan
    0.06
    Act Density 0.013%

    No Known Activations