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

    Neuronpedia

    INDEX
    Explanations

    viewport description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tra
    0.46
    有
    0.43
    assapi
    0.41
     áll
    0.40
    St
    0.40
    ス
    0.39
    स
    0.39
    Trans
    0.39
    Sh
    0.38
    Don
    0.38
    POSITIVE LOGITS
     descriptor
    0.44
     motivator
    0.41
     description
    0.40
     intent
    0.40
     carburetor
    0.40
     describ
    0.39
     explanatory
    0.38
    ্যেষ্ঠ
    0.38
     bitrate
    0.38
     describing
    0.38
    Act Density 0.002%

    No Known Activations