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

    Neuronpedia

    INDEX
    Explanations

    an adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    个数
    0.93
    и
    0.93
    R
    0.90
    ος
    0.89
    I
    0.86
    व
    0.85
    t
    0.84
     vissza
    0.81
    J
    0.79
    Jika
    0.78
    POSITIVE LOGITS
     ২৯
    0.88
     situational
    0.83
     script
    0.82
     member
    0.81
     statute
    0.80
     stamped
    0.80
     beant
    0.79
     metadata
    0.79
     eletr
    0.79
     timestamp
    0.78
    Act Density 0.295%

    No Known Activations