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

    Neuronpedia

    INDEX
    Explanations

    Minecraft

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुर
    -0.07
    	token
    -0.07
     buckets
    -0.06
    udur
    -0.06
    beat
    -0.06
     taboo
    -0.06
    .ElementAt
    -0.06
     surprising
    -0.06
    ottes
    -0.06
    udents
    -0.06
    POSITIVE LOGITS
     Forest
    0.07
     MX
    0.06
    爽
    0.06
    金额
    0.06
     Melee
    0.06
    	RTLR
    0.06
    .didReceiveMemoryWarning
    0.06
     Vince
    0.06
     Mechanical
    0.06
     معدن
    0.06
    Act Density 0.002%

    No Known Activations