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

    Neuronpedia

    INDEX
    Explanations

    Stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ship
    -0.06
    ってる
    -0.06
     radioButton
    -0.06
     Platforms
    -0.06
    ительный
    -0.06
     poignant
    -0.06
     dö
    -0.06
     thi
    -0.06
     졸업
    -0.06
    Congress
    -0.06
    POSITIVE LOGITS
    Compiled
    0.07
    (initial
    0.07
     Đặc
    0.07
    >');↵
    0.07
    Caps
    0.06
    осред
    0.06
    STEP
    0.06
    .GetSize
    0.06
     çünkü
    0.06
     Cartesian
    0.06
    Act Density 0.287%

    No Known Activations