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

    Neuronpedia

    INDEX
    Explanations

    symbolic reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לאורך
    -0.08
     maç
    -0.08
     ale
    -0.08
     bient
    -0.07
     ඇ
    -0.07
     foran
    -0.07
    ']],↵
    -0.07
     miatt
    -0.07
     både
    -0.07
     характера
    -0.07
    POSITIVE LOGITS
     theoretically
    0.08
     mümkün
    0.08
    ্টো
    0.07
     сокращ
    0.07
    rd
    0.07
    erlijke
    0.07
     (?)
    0.07
    cuits
    0.07
     भरो
    0.07
    ential
    0.07
    Act Density 0.060%

    No Known Activations