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

    Neuronpedia

    INDEX
    Explanations

    traditional names and success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ju
    0.43
     farming
    0.40
    unk
    0.38
    ч
    0.38
     souh
    0.38
     पहुंचाने
    0.38
    ’,
    0.37
     prices
    0.37
     कीमतें
    0.37
     h
    0.36
    POSITIVE LOGITS
     sicherlich
    0.52
    🎍
    0.46
    💠
    0.46
    成功
    0.46
    🚥
    0.45
     assured
    0.43
     succeeded
    0.43
    📎
    0.43
     sicuramente
    0.43
    Success
    0.43
    Act Density 0.001%

    No Known Activations