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

    Neuronpedia

    INDEX
    Explanations

    Code with "the" or "if"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    736
    -0.07
     rất
    -0.07
    723
    -0.07
    ]*(
    -0.07
    。(
    -0.06
    .An
    -0.06
    .M
    -0.06
    bach
    -0.06
     Indianapolis
    -0.06
     Tamb
    -0.06
    POSITIVE LOGITS
    rypto
    0.06
     crafting
    0.06
    .debian
    0.05
     ming
    0.05
    ธ
    0.05
     immortal
    0.05
    普通
    0.05
    /re
    0.05
    .hide
    0.05
    øj
    0.05
    Act Density 0.009%

    No Known Activations