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

    Neuronpedia

    INDEX
    Explanations

    too much / excessively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    但
    0.26
    Deze
    0.26
    ី
    0.25
    Additionally
    0.25
    Revenue
    0.25
    Moment
    0.25
    することで
    0.24
    がありますが
    0.24
    crafted
    0.24
    K
    0.24
    POSITIVE LOGITS
     слишком
    0.41
     too
    0.39
     hopelessly
    0.39
     troppo
    0.39
     demasiado
    0.38
     Too
    0.37
     terlalu
    0.36
     너무
    0.35
     alas
    0.35
    too
    0.34
    Act Density 0.001%

    No Known Activations