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

    Neuronpedia

    INDEX
    Explanations

    tailored for specific needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    নিষ্ঠ
    0.40
     ಭ
    0.39
    back
    0.38
    iler
    0.36
     promise
    0.36
    a
    0.35
    future
    0.35
    Sal
    0.35
    Teacher
    0.34
    padding
    0.34
    POSITIVE LOGITS
     toward
    0.61
     towards
    0.56
     hacia
    0.55
     نحو
    0.53
     Toward
    0.49
     към
    0.48
     jurul
    0.47
    Toward
    0.47
    向
    0.46
    tow
    0.45
    Act Density 0.009%

    No Known Activations