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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌باشد
    -0.07
     ICON
    -0.07
    	open
    -0.07
    .nz
    -0.06
    より
    -0.06
     giúp
    -0.06
     searched
    -0.06
    Neg
    -0.06
     учнів
    -0.06
     analyzed
    -0.06
    POSITIVE LOGITS
    цем
    0.07
    VE
    0.06
     boo
    0.06
    Unlock
    0.06
     oto
    0.06
    template
    0.06
     cánh
    0.06
    ой
    0.06
     orch
    0.06
     unpopular
    0.06
    Act Density 0.003%

    No Known Activations