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

    Neuronpedia

    INDEX
    Explanations

    stock tickers and brands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ander
    0.59
    groovy
    0.58
     Thrust
    0.58
    Bennett
    0.58
     Auf
    0.57
     ara
    0.56
     Gonzales
    0.56
     AU
    0.55
     Grover
    0.55
    Brown
    0.55
    POSITIVE LOGITS
    ída
    0.62
     FAILURE
    0.58
    persky
    0.54
    貘
    0.54
    啣
    0.54
    TableName
    0.53
    캅
    0.52
     malfunction
    0.52
     الفريق
    0.52
    poetrylovers
    0.52
    Act Density 0.000%

    No Known Activations