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

    Neuronpedia

    INDEX
    Explanations

    criminal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -am
    -0.07
     Nes
    -0.07
    CUS
    -0.07
    性
    -0.07
     collusion
    -0.06
     scalability
    -0.06
    /plain
    -0.06
     sao
    -0.06
    gent
    -0.06
     nem
    -0.06
    POSITIVE LOGITS
     Listed
    0.07
    絵
    0.06
     듣
    0.06
    imi
    0.06
    ="/">↵
    0.06
     gerekli
    0.06
     своим
    0.06
    ìm
    0.06
     عبدال
    0.06
    ो।
    0.06
    Act Density 0.016%

    No Known Activations