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

    Neuronpedia

    INDEX
    Explanations

    breakdown covering what how why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    または
    0.49
    거나
    0.48
     அல்லது
    0.47
    或者
    0.46
    하거나
    0.46
     または
    0.46
    あるいは
    0.44
     ወይም
    0.43
    หรือ
    0.43
     또는
    0.43
    POSITIVE LOGITS
     its
    0.50
     it
    0.45
     benefits
    0.45
    Isn
    0.44
     encompasses
    0.44
     ew
    0.44
     incredibly
    0.42
    Its
    0.42
     functions
    0.41
     célèbre
    0.41
    Act Density 0.207%

    No Known Activations