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

    Neuronpedia

    INDEX
    Explanations

    junior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	margin
    -0.07
    uffed
    -0.07
    async
    -0.07
     infrared
    -0.07
     Porter
    -0.07
    Room
    -0.07
     chased
    -0.07
    inscription
    -0.07
    跑步
    -0.06
     phóng
    -0.06
    POSITIVE LOGITS
     Petroleum
    0.07
    最初的
    0.07
     พฤษภา
    0.07
    했던
    0.07
    ]=='
    0.07
     ApiController
    0.07
    キャンペーン
    0.07
    UILabel
    0.06
    .''
    0.06
    עשייה
    0.06
    Act Density 0.009%

    No Known Activations