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

    Neuronpedia

    INDEX
    Explanations

    Indian names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    孟
    0.46
     দিল্লির
    0.40
     Malhotra
    0.40
     Hindi
    0.39
     बनर्जी
    0.39
     Mishra
    0.38
     शोध
    0.38
     Dubey
    0.38
     упо
    0.37
    ᆸ
    0.37
    POSITIVE LOGITS
     detached
    0.46
     చక్ర
    0.44
    ith
    0.43
    ahorse
    0.43
    岚
    0.42
    itha
    0.41
     crank
    0.41
    akaran
    0.40
    othy
    0.39
    Likewise
    0.39
    Act Density 0.005%

    No Known Activations