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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coffee
    -0.08
    עי
    -0.07
    =tf
    -0.07
    	pl
    -0.07
    _proba
    -0.07
    _MetadataUsageId
    -0.07
    	filter
    -0.06
     LinkedList
    -0.06
     environment
    -0.06
     ProductService
    -0.06
    POSITIVE LOGITS
     SEARCH
    0.08
     dangerously
    0.08
    不变
    0.07
    .remote
    0.07
    从容
    0.07
    膀
    0.07
     manages
    0.07
     الان
    0.07
     Bits
    0.07
    最后一个
    0.07
    Act Density 0.038%

    No Known Activations