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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ）の
    -0.07
    .lst
    -0.07
    (guild
    -0.07
    寄
    -0.07
    高い
    -0.07
    。她
    -0.06
     đồng
    -0.06
     frosting
    -0.06
     بازیگر
    -0.06
     dương
    -0.06
    POSITIVE LOGITS
     मह
    0.06
    (original
    0.06
     ag
    0.06
     dub
    0.06
    axed
    0.06
     boots
    0.06
    ++)↵
    0.06
    esium
    0.06
    斯特
    0.06
     Census
    0.06
    Act Density 0.000%

    No Known Activations