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

    Neuronpedia

    INDEX
    Explanations

    are concerned or struggling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nejen
    0.43
     或者
    0.35
     这个
    0.34
    ιστή
    0.33
     هذا
    0.32
     hoặc
    0.32
    不但
    0.32
    AllCaps
    0.32
     Ovaj
    0.32
     alebo
    0.31
    POSITIVE LOGITS
     privind
    0.37
    的其他
    0.37
     innych
    0.37
     અન્ય
    0.37
     иных
    0.36
    ની
    0.35
    อื่นๆ
    0.35
     अन्य
    0.35
     других
    0.34
     generell
    0.34
    Act Density 0.188%

    No Known Activations