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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [Y
    -0.07
     went
    -0.07
    学生
    -0.07
     моря
    -0.07
     کل
    -0.07
    ер
    -0.07
     정부
    -0.06
    ΑΔ
    -0.06
    �
    -0.06
     react
    -0.06
    POSITIVE LOGITS
    termin
    0.06
    -produ
    0.06
    outside
    0.06
    .SpringBootApplication
    0.06
    зн
    0.06
    /pre
    0.06
    massage
    0.06
    xda
    0.06
    leading
    0.06
    -target
    0.06
    Act Density 0.001%

    No Known Activations