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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    「え
    -0.07
    らず
    -0.07
     své
    -0.06
     designs
    -0.06
     Drawer
    -0.06
    -0.06
    	List
    -0.06
     ห
    -0.06
     voks
    -0.06
     Relatives
    -0.06
    POSITIVE LOGITS
     Italia
    0.07
    archs
    0.07
     кажд
    0.07
    icopt
    0.07
     unknow
    0.06
    ("../../
    0.06
    PLAN
    0.06
     murder
    0.06
     unexpectedly
    0.06
    RAFT
    0.06
    Act Density 0.286%

    No Known Activations