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

    Neuronpedia

    INDEX
    Explanations

    removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    個
    -0.06
     sensations
    -0.06
    .epoch
    -0.06
     souls
    -0.06
    ’an
    -0.06
     المر
    -0.06
     الف
    -0.06
     ά
    -0.06
    #af
    -0.06
     rapid
    -0.06
    POSITIVE LOGITS
    dire
    0.07
    níci
    0.07
    (Array
    0.06
     traded
    0.06
    		↵↵
    0.06
    ोल
    0.06
             
    0.06
    sponsor
    0.06
    exels
    0.06
    empo
    0.06
    Act Density 0.013%

    No Known Activations