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

    Neuronpedia

    INDEX
    Explanations

    Strategic location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aux
    -0.07
    讹
    -0.07
    𝘦
    -0.07
     Rick
    -0.07
     Helen
    -0.06
    êt
    -0.06
     vector
    -0.06
    试
    -0.06
    evil
    -0.06
     cruelty
    -0.06
    POSITIVE LOGITS
     hairs
    0.07
    manın
    0.07
    _func
    0.07
    田园
    0.07
     multiprocessing
    0.07
    ניק
    0.07
     proble
    0.07
    	work
    0.06
    .tab
    0.06
    datatable
    0.06
    Act Density 0.031%

    No Known Activations