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

    Neuronpedia

    INDEX
    Explanations

    volatile flammable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {,
    0.49
    质疑
    0.40
    Uploading
    0.38
    ренности
    0.37
    余
    0.37
    Upload
    0.36
     McCoy
    0.36
     एलर्जी
    0.36
     выборе
    0.36
     आकाश
    0.36
    POSITIVE LOGITS
     couldn
    0.57
     सदन
    0.44
    Couldn
    0.44
     Couldn
    0.42
     cracked
    0.39
     haven
    0.39
    سن
    0.39
     wouldn
    0.38
     canons
    0.37
     wasn
    0.37
    Act Density 0.000%

    No Known Activations