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

    Neuronpedia

    INDEX
    Explanations

    installed or functioning components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бойынша
    0.85
     meliputi
    0.84
     ersche
    0.81
    skcipher
    0.79
     keseluruhan
    0.76
     dolayı
    0.76
    성은
    0.75
    성에
    0.75
    сли
    0.73
     হেসে
    0.72
    POSITIVE LOGITS
     installed
    2.06
     positioned
    2.00
     located
    1.99
     situated
    1.97
     configured
    1.97
     stationed
    1.96
     mounted
    1.90
     deployed
    1.87
     connected
    1.86
     placed
    1.82
    Act Density 0.382%

    No Known Activations