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

    Neuronpedia

    INDEX
    Explanations

    reinforce

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    局
    -0.07
    ☯
    -0.07
    融媒体
    -0.07
    阐
    -0.07
     Thương
    -0.07
    古镇
    -0.07
    宏观经济
    -0.07
    ӑ
    -0.07
    .Ticks
    -0.07
    拈
    -0.07
    POSITIVE LOGITS
     configurations
    0.07
     ks
    0.07
     reinforcement
    0.07
    當然
    0.07
     favorite
    0.07
     reinforces
    0.06
    "name
    0.06
    dater
    0.06
    .Configuration
    0.06
    源泉
    0.06
    Act Density 0.009%

    No Known Activations