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

    Neuronpedia

    INDEX
    Explanations

    write a request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     основном
    0.36
     самой
    0.36
     Zenith
    0.36
     ViewHolder
    0.36
     మొద
    0.35
    atthakath
    0.35
     Declan
    0.35
     illa
    0.35
     Rankin
    0.35
     rinsing
    0.34
    POSITIVE LOGITS
    What
    0.51
    Python
    0.48
    How
    0.46
    Code
    0.42
    ادی
    0.42
    代码
    0.41
    Ą
    0.40
     code
    0.40
    Linux
    0.39
    Describe
    0.39
    Act Density 0.748%

    No Known Activations