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

    Neuronpedia

    INDEX
    Explanations

    representation and format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    all
    0.45
    各地
    0.44
    ificada
    0.43
    እና
    0.43
    hota
    0.42
    朧
    0.41
    清新
    0.41
    ον
    0.40
    Kami
    0.40
    这意味着
    0.40
    POSITIVE LOGITS
     syntactic
    0.45
     Format
    0.43
    𝚂
    0.43
     UNIX
    0.43
     fermeture
    0.43
     genotypes
    0.42
     syntax
    0.42
     mutex
    0.41
    ToString
    0.41
    রোধ
    0.41
    Act Density 0.001%

    No Known Activations