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

    Neuronpedia

    INDEX
    Explanations

    highest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blair
    -0.07
     SSA
    -0.07
    Ｋ
    -0.06
     Pharma
    -0.06
    иль
    -0.06
    nan
    -0.06
     fans
    -0.06
     BUILD
    -0.06
     یاد
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     highest
    0.13
     Highest
    0.09
    highest
    0.08
    Highest
    0.08
     within
    0.07
     utmost
    0.06
    Maximum
    0.06
    CATEGORY
    0.06
    HING
    0.06
     máme
    0.06
    Act Density 0.008%

    No Known Activations