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

    Neuronpedia

    INDEX
    Explanations

    compress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اسب
    -0.06
    chat
    -0.06
    RoleId
    -0.06
     эф
    -0.06
    ComputedStyle
    -0.06
     repetitions
    -0.06
    سلام
    -0.06
    构
    -0.06
    幼
    -0.06
    delivr
    -0.06
    POSITIVE LOGITS
     капит
    0.07
     schem
    0.07
    可是
    0.06
    )n
    0.06
     isn
    0.06
     ISS
    0.06
     aren
    0.06
    .EventArgs
    0.06
     responsable
    0.06
    ↵                    ↵
    0.06
    Act Density 0.001%

    No Known Activations