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

    Neuronpedia

    INDEX
    Explanations

    watch?v= and watchtower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    صول
    0.42
     glacial
    0.40
     Cloud
    0.39
    antica
    0.38
    razine
    0.38
    henium
    0.38
    fluence
    0.38
     Aoki
    0.38
     Anaconda
    0.37
     Yun
    0.37
    POSITIVE LOGITS
     腕時計
    0.54
    腕時計
    0.47
    Watch
    0.46
    tower
    0.45
    watch
    0.45
    Alarm
    0.45
    fulness
    0.43
     İlçesi
    0.42
     watch
    0.42
     Watch
    0.42
    Act Density 0.003%

    No Known Activations