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

    Neuronpedia

    INDEX
    Explanations

    essential to consult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    昌
    0.71
    arella
    0.70
    лә
    0.70
     CLL
    0.69
    aso
    0.69
    ләр
    0.69
    тельству
    0.67
    <unused30>
    0.64
    ینہ
    0.64
    дження
    0.63
    POSITIVE LOGITS
     Places
    0.88
     Coconut
    0.84
    !:
    0.84
     Outdoor
    0.82
     Obviously
    0.81
     People
    0.81
    ቃት
    0.80
     Concerned
    0.80
     Away
    0.80
     SHOULD
    0.79
    Act Density 0.004%

    No Known Activations