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

    Neuronpedia

    INDEX
    Explanations

    save the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    兟
    0.37
    ުރު
    0.37
    geqslant
    0.36
     туда
    0.36
    ដល់
    0.36
    UINT
    0.36
    يميديا
    0.35
    ..</
    0.35
     guar
    0.35
    cial
    0.35
    POSITIVE LOGITS
     createFile
    0.40
    创建一个
    0.40
     těchto
    0.39
     genannten
    0.39
     Ast
    0.38
     נו
    0.38
     Created
    0.38
     Create
    0.37
    creates
    0.37
     νο
    0.37
    Act Density 0.003%

    No Known Activations