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

    Neuronpedia

    INDEX
    Explanations

    terrorism and related acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    laquo
    1.06
     columnIndex
    1.02
     คณิต
    1.02
     bebida
    1.01
     đang
    1.00
     functioned
    0.97
    獼
    0.97
     hesitant
    0.96
    ▌
    0.96
    0.95
    POSITIVE LOGITS
    까
    0.92
    }$
    0.89
    दा
    0.89
    ج
    0.84
     merk
    0.84
    STS
    0.83
    NJ
    0.82
    ره
    0.80
    ع
    0.79
    м
    0.77
    Act Density 0.058%

    No Known Activations