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

    Neuronpedia

    INDEX
    Explanations

    code syntax, delimiters, separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    who
    0.55
    เพราะ
    0.53
    citizen
    0.52
    Citizens
    0.52
    Taj
    0.52
    Indianapolis
    0.52
    medical
    0.51
    political
    0.51
    anskje
    0.51
    Police
    0.51
    POSITIVE LOGITS
     eukaryotes
    0.60
     生命周期
    0.58
     வரலாறு
    0.57
     conceptually
    0.57
     formalism
    0.55
     Initializes
    0.54
     இந்நிலையில்
    0.54
     yeasts
    0.54
     pathogens
    0.53
     まず
    0.53
    Act Density 0.024%

    No Known Activations