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

    Neuronpedia

    INDEX
    Explanations

    programming language imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     On
    0.42
     Page
    0.40
     Muscat
    0.39
     Append
    0.37
     Ombudsman
    0.37
     Bond
    0.36
     Account
    0.36
    특별
    0.36
     Bonds
    0.35
     Altogether
    0.35
    POSITIVE LOGITS
     kotlin
    0.45
     scarred
    0.42
     asalamualaikum
    0.41
    ্প্র
    0.41
    ianic
    0.39
    珐
    0.39
    ierstrass
    0.38
    java
    0.38
     tble
    0.38
     obliquely
    0.38
    Act Density 0.000%

    No Known Activations