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

    Neuronpedia

    INDEX
    Explanations

    TV and radio media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ių
    0.38
     মোর
    0.38
     Essence
    0.37
     Burger
    0.36
    ("--------
    0.35
    孙
    0.34
    饿
    0.34
     构建
    0.34
     mora
    0.33
    充满
    0.33
    POSITIVE LOGITS
    番組
    0.56
    📺
    0.54
    节目
    0.53
     stations
    0.52
     station
    0.49
     tv
    0.49
    电视
    0.49
     TV
    0.49
    tv
    0.48
     televisión
    0.47
    Act Density 0.007%

    No Known Activations