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

    Neuronpedia

    INDEX
    Explanations

    /2 sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused22>
    0.45
    <unused24>
    0.39
     znajdu
    0.39
     което
    0.38
     సహాయ
    0.38
     besitzt
    0.38
    DUCT
    0.38
    }}=-
    0.37
     গিয়াছেন
    0.37
    繽
    0.36
    POSITIVE LOGITS
    Selector
    0.42
     eventual
    0.38
    กรรม
    0.35
    Box
    0.34
     actuar
    0.34
     eventually
    0.34
     overtime
    0.34
     hourly
    0.33
     Mait
    0.33
     anonym
    0.33
    Act Density 0.000%

    No Known Activations