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

    Neuronpedia

    INDEX
    Explanations

    configuration Enablers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نا
    0.97
    𝓃
    0.76
    ת
    0.76
    ನಗೆ
    0.75
    α
    0.75
    ía
    0.68
    tight
    0.68
    спо
    0.65
    uur
    0.65
    ాత
    0.64
    POSITIVE LOGITS
     Realtors
    0.91
     PTR
    0.89
     Э
    0.88
     Websites
    0.86
     ventilators
    0.86
     Қ
    0.85
     Tourists
    0.84
     Buses
    0.84
     Firstly
    0.83
     enterprises
    0.82
    Act Density 0.001%

    No Known Activations