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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    灵
    -0.07
    .conv
    -0.07
     dubbed
    -0.06
     такими
    -0.06
     Represents
    -0.06
    نان
    -0.06
    τέρα
    -0.06
     indictment
    -0.06
    Gem
    -0.06
    .series
    -0.06
    POSITIVE LOGITS
     ویکی
    0.07
    .setResult
    0.06
    Billing
    0.06
    vpn
    0.06
     timing
    0.06
    composer
    0.06
    who
    0.06
     Shi
    0.06
    描
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations