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

    Neuronpedia

    INDEX
    Explanations

    making a decision

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    大
    -0.07
    本身就
    -0.07
    uestas
    -0.07
    隔着
    -0.06
     irrelevant
    -0.06
     relegated
    -0.06
     Regardless
    -0.06
     Somalia
    -0.06
     Jed
    -0.06
    饺子
    -0.06
    POSITIVE LOGITS
    .";
↵
    0.08
     listeners
    0.08
     ..."↵↵
    0.07
     öğrenciler
    0.07
    ."),
    0.07
     "{}
    0.07
    ("/")↵
    0.07
    ！↵↵
    0.07
    (click
    0.07
    ┘
    0.06
    Act Density 0.041%

    No Known Activations