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

    Neuronpedia

    INDEX
    Explanations

    google drive links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acoust
    0.43
     superficies
    0.39
    ণ্ডল
    0.38
    Stokes
    0.38
    Gib
    0.38
     thermodynam
    0.38
    Tut
    0.37
     liczb
    0.37
     acúst
    0.37
    Hier
    0.37
    POSITIVE LOGITS
     Google
    0.70
    Google
    0.61
     google
    0.59
     Drive
    0.54
     drive
    0.52
     गूगल
    0.51
    ドライブ
    0.49
     DRIVE
    0.44
    GOOGLE
    0.44
    google
    0.44
    Act Density 0.018%

    No Known Activations