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

    Neuronpedia

    INDEX
    Explanations

    high + modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     height
    0.93
     Height
    0.88
     высота
    0.86
     Hig
    0.85
    notch
    0.85
    Height
    0.84
     پایین
    0.83
    height
    0.83
     높
    0.82
     মানের
    0.81
    POSITIVE LOGITS
     app
    0.67
    zei
    0.66
     зав
    0.64
    辶
    0.63
     repatri
    0.62
     இடம்பெ
    0.62
    ays
    0.62
    цеп
    0.61
    țiuni
    0.61
    ộp
    0.61
    Act Density 0.080%

    No Known Activations