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

    Neuronpedia

    INDEX
    Explanations

    locations or specific things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     syllable
    0.38
    However
    0.37
     breakdown
    0.36
     However
    0.34
     rejected
    0.34
     plantation
    0.34
     Plantation
    0.33
     bromide
    0.32
     player
    0.32
     maar
    0.32
    POSITIVE LOGITS
     이곳
    0.40
     मानता
    0.37
     꿈
    0.36
     하늘
    0.36
     வார
    0.36
     HOSP
    0.36
    쭤
    0.35
    𒋼
    0.35
    雔
    0.35
    菁
    0.35
    Act Density 0.099%

    No Known Activations