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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מים
    -0.07
     inval
    -0.07
    暴雨
    -0.07
    rasing
    -0.07
     shy
    -0.06
    restore
    -0.06
     richt
    -0.06
    島
    -0.06
    ********************************************************************************
    -0.06
    ISON
    -0.06
    POSITIVE LOGITS
     Stamina
    0.08
     Yük
    0.07
    给我
    0.07
     الطفل
    0.07
     לי
    0.07
    ogra
    0.07
     Cultural
    0.07
     oferta
    0.07
     Pharma
    0.07
     Corruption
    0.06
    Act Density 0.025%

    No Known Activations