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

    Neuronpedia

    INDEX
    Explanations

    particle number or void fraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bound
    0.40
    Person
    0.38
    Legal
    0.38
    Spo
    0.38
    Committee
    0.38
    Highway
    0.38
    Essentials
    0.38
    삶
    0.38
    Ends
    0.37
    Spoiler
    0.37
    POSITIVE LOGITS
    reporter
    0.42
     ataupun
    0.41
     esclare
    0.40
     mechanistic
    0.39
     yaitu
    0.38
     Ert
    0.38
     namely
    0.37
     kinetic
    0.37
     industri
    0.37
     UFC
    0.37
    Act Density 0.001%

    No Known Activations