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

    Neuronpedia

    INDEX
    Explanations

    console.log calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coefficient
    0.45
    retrofit
    0.43
    hydroxy
    0.42
    ARDS
    0.42
    ÈME
    0.42
     серд
    0.42
    Hydroxy
    0.42
    罌
    0.41
    酞
    0.40
    個人的
    0.40
    POSITIVE LOGITS
     log
    1.02
    log
    0.88
     logs
    0.74
     Log
    0.70
     로그
    0.64
    Log
    0.63
     console
    0.61
     Logs
    0.59
     लॉग
    0.58
     Console
    0.57
    Act Density 0.005%

    No Known Activations