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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     previamente
    -0.10
     preth
    -0.08
     ؛
    -0.08
     gecombine
    -0.08
    联合
    -0.08
     تخصص
    -0.08
    驻
    -0.08
     કરશે
    -0.08
    。目前
    -0.08
    Dedicated
    -0.08
    POSITIVE LOGITS
     famously
    0.13
     personnages
    0.13
     protagonist
    0.13
     കഥാപാത്ര
    0.12
     personagens
    0.11
    Throughout
    0.11
     চর
    0.10
     titular
    0.10
     narrator
    0.10
    主人
    0.10
    Act Density 0.049%

    No Known Activations