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

    Neuronpedia

    INDEX
    Explanations

    where available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾನೆ
    0.26
    HSI
    0.25
     profesor
    0.25
    റ്റു
    0.25
     wohl
    0.25
    URER
    0.24
    atanam
    0.24
    🟩
    0.24
    खबर
    0.23
    venth
    0.23
    POSITIVE LOGITS
     కొన్ని
    0.28
     Convenience
    0.27
    Conven
    0.27
    stringify
    0.27
     few
    0.26
    Whenever
    0.26
     Construction
    0.26
     Whenever
    0.26
     whenever
    0.25
     Lind
    0.25
    Act Density 0.087%

    No Known Activations