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

    Neuronpedia

    INDEX
    Explanations

    setup and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Completion
    0.43
     plastic
    0.39
    Signing
    0.38
    টিয়া
    0.37
    FBSDKAppEvents
    0.36
    Plastic
    0.35
    Button
    0.35
    Device
    0.35
    Wifi
    0.35
     appart
    0.34
    POSITIVE LOGITS
     desta
    0.47
     Eriksson
    0.42
     debat
    0.41
     చర్చ
    0.41
    masing
    0.40
     misguided
    0.40
     обсужда
    0.40
     estrategias
    0.39
     aspectos
    0.39
    大きさ
    0.39
    Act Density 0.000%

    No Known Activations