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

    Neuronpedia

    INDEX
    Explanations

    Modern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fit
    -0.07
     Avalanche
    -0.06
     hastalık
    -0.06
     FAILURE
    -0.06
     baj
    -0.06
    >$
    -0.06
    .Fail
    -0.06
     derived
    -0.06
     beste
    -0.06
     warranted
    -0.06
    POSITIVE LOGITS
     strchr
    0.07
    族自治
    0.07
     คณะ
    0.07
     Pom
    0.07
     Uttar
    0.06
     �
    0.06
    正常
    0.06
     upkeep
    0.06
     первой
    0.06
    стан
    0.06
    Act Density 0.016%

    No Known Activations