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

    Neuronpedia

    INDEX
    Explanations

    multiple languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тата
    0.47
    n
    0.44
    s
    0.44
     blog
    0.43
    ir
    0.43
    entra
    0.42
     dark
    0.41
    一流
    0.41
     filtre
    0.41
     bastion
    0.41
    POSITIVE LOGITS
     suivants
    0.56
     ಉಪಯೋಗ
    0.55
    Შ
    0.55
    ገልግሎ
    0.51
    қу
    0.50
    լ
    0.48
    ?\\
    0.46
    を持っている
    0.46
    ERSON
    0.45
    ិក
    0.45
    Act Density 0.000%

    No Known Activations