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

    Neuronpedia

    INDEX
    Explanations

    definitions and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    δος
    0.50
     Bred
    0.50
     الجذر
    0.44
     লক্ষ্য
    0.42
    യിലേക്ക്
    0.41
    attva
    0.41
     spectral
    0.40
    itionally
    0.40
     Shed
    0.40
     Zwischen
    0.40
    POSITIVE LOGITS
    ני
    0.54
    ш
    0.51
     ой
    0.49
     больше
    0.48
     лу
    0.47
    ним
    0.46
    мень
    0.46
     по
    0.46
     ар
    0.45
    ником
    0.45
    Act Density 0.001%

    No Known Activations