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

    Neuronpedia

    INDEX
    Explanations

    computer instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ależ
    0.46
    illiams
    0.44
    በባ
    0.44
     ग्ले
    0.43
    干燥
    0.42
    เปลี่ยน
    0.41
    owers
    0.40
    ပေါင်း
    0.40
     нанесе
    0.40
     drier
    0.40
    POSITIVE LOGITS
     rationality
    0.47
     NULL
    0.46
     it
    0.46
    EXIT
    0.46
     panic
    0.45
     zipcode
    0.43
     intelectual
    0.42
    하고
    0.42
     dwRes
    0.42
     isn
    0.41
    Act Density 0.017%

    No Known Activations