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

    Neuronpedia

    INDEX
    Explanations

    Images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mos
    -0.07
    Firebase
    -0.07
    进入
    -0.06
    ाब
    -0.06
     Mos
    -0.06
     chores
    -0.06
    قاء
    -0.06
    Christmas
    -0.06
     Barker
    -0.06
     perme
    -0.06
    POSITIVE LOGITS
     нар
    0.07
    	ap
    0.06
     cement
    0.06
    alsex
    0.06
    abis
    0.06
     हट
    0.06
    Occurrences
    0.06
    Beans
    0.06
    .ALL
    0.06
    815
    0.06
    Act Density 0.005%

    No Known Activations