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

    Neuronpedia

    INDEX
    Explanations

    Patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    」。
    -0.07
    Eat
    -0.07
     ids
    -0.07
    kur
    -0.07
    >P
    -0.07
     прес
    -0.06
     Talks
    -0.06
    ських
    -0.06
     Gus
    -0.06
    kap
    -0.06
    POSITIVE LOGITS
     bỏ
    0.07
     genetically
    0.06
     Carm
    0.06
     affiliated
    0.06
    黨
    0.06
     gehört
    0.06
    snow
    0.06
     thanking
    0.06
     Communications
    0.06
    робіт
    0.06
    Act Density 0.003%

    No Known Activations