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

    Neuronpedia

    INDEX
    Explanations

    water and density

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    თავ
    0.42
    マンス
    0.39
     sols
    0.37
     नव्या
    0.37
    グッズ
    0.37
    newData
    0.36
     new
    0.36
    庸
    0.36
     buckets
    0.35
     ஒதுக்க
    0.35
    POSITIVE LOGITS
    Philippines
    0.44
    Shiv
    0.42
     Empres
    0.41
     корм
    0.40
     እ
    0.39
    🦜
    0.39
     Philippines
    0.39
     reprim
    0.39
     Shiv
    0.38
     puesto
    0.38
    Act Density 0.000%

    No Known Activations