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

    Neuronpedia

    INDEX
    Explanations

    success and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flooded
    0.48
     humide
    0.47
     primitives
    0.44
     congestion
    0.43
     clogged
    0.43
     unusable
    0.42
     usability
    0.42
     curious
    0.41
     demod
    0.41
     giãn
    0.41
    POSITIVE LOGITS
     success
    1.56
     성공
    1.45
     Success
    1.41
     успеха
    1.38
    Success
    1.34
    成功的
    1.34
    success
    1.34
     sukces
    1.32
    成功
    1.31
     achievements
    1.31
    Act Density 0.051%

    No Known Activations