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

    Neuronpedia

    INDEX
    Explanations

    yolk, battery, torque

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     перед
    0.49
    ্রাজ
    0.48
    巉
    0.48
     संजीव
    0.46
    0.46
     OG
    0.46
    鿌
    0.46
     Refs
    0.45
    芰
    0.45
    rakech
    0.45
    POSITIVE LOGITS
     collect
    0.52
     compile
    0.50
    รี
    0.50
     cole
    0.50
     brush
    0.49
    D
    0.48
    Saudi
    0.47
     compartment
    0.46
     immersed
    0.46
     characteristic
    0.45
    Act Density 0.001%

    No Known Activations