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

    Neuronpedia

    INDEX
    Explanations

    being attacked or overwhelmed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。　　
    -2.25
    酲
    -2.16
    ‪.‬‬
    -2.02
    馐
    -2.02
    na
    -2.02
    as
    -2.02
    本章
    -2.00
    谞
    -1.99
    va
    -1.98
     şi
    -1.97
    POSITIVE LOGITS
    }
    2.34
    ↵
    2.22
     the
    2.06
    嚀
    2.05
    无比
    2.00
      
    1.97
     it
    1.83
    霂
    1.76
     respald
    1.74
    因为他
    1.73
    Act Density 0.004%

    No Known Activations